@justjoshn/pi-pstack-v2 0.0.0-stage → 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +22 -0
- package/README.md +66 -2
- package/agents/ci-watcher.md +26 -0
- package/agents/comment-sicko.md +32 -0
- package/agents/poteto-agent.md +8 -0
- package/agents/thermo-nuclear-code-quality-review.md +23 -0
- package/docs/guide/01-setup.md +81 -0
- package/docs/guide/02-poteto-mode.md +137 -0
- package/docs/guide/03-understand.md +79 -0
- package/docs/guide/04-design.md +133 -0
- package/docs/guide/05-build-and-clean.md +83 -0
- package/docs/guide/06-verify-and-ship.md +162 -0
- package/docs/guide/07-overnight.md +121 -0
- package/docs/guide/08-principles.md +72 -0
- package/docs/guide/09-make-it-yours.md +100 -0
- package/docs/guide/10-recipes-and-pitfalls.md +182 -0
- package/docs/guide/README.md +38 -0
- package/docs/guide/images/design.jpg +0 -0
- package/docs/guide/images/overnight.jpg +0 -0
- package/docs/guide/images/recipes.jpg +0 -0
- package/docs/guide/images/router.jpg +0 -0
- package/docs/guide/images/understanding.jpg +0 -0
- package/docs/guide/images/verification.jpg +0 -0
- package/docs/pi-mechanisms.md +101 -0
- package/package.json +49 -4
- package/rules/no-inline-imports.md +8 -0
- package/rules/typescript-exhaustive-switch.md +6 -0
- package/skills/architect/SKILL.md +81 -0
- package/skills/architect/references/design-red-flags.md +57 -0
- package/skills/architect/references/rationale-template.md +35 -0
- package/skills/architect/references/runner-prompt.md +20 -0
- package/skills/arena/SKILL.md +48 -0
- package/skills/automate-me/SKILL.md +104 -0
- package/skills/benchmark-checklist/SKILL.md +39 -0
- package/skills/blast-radius/SKILL.md +50 -0
- package/skills/bro/SKILL.md +7 -0
- package/skills/check-compiler-errors/SKILL.md +23 -0
- package/skills/control-cli/SKILL.md +110 -0
- package/skills/control-ui/SKILL.md +109 -0
- package/skills/correct/SKILL.md +32 -0
- package/skills/create-formal-verification-skill/SKILL.md +43 -0
- package/skills/create-verification-skill/SKILL.md +44 -0
- package/skills/create-verification-skill/references/feature-map-example/README.md +47 -0
- package/skills/create-verification-skill/references/feature-map-example/create-note.md +39 -0
- package/skills/create-verification-skill/references/feature-map-example/search.md +45 -0
- package/skills/deslop/SKILL.md +22 -0
- package/skills/figure-it-out/SKILL.md +54 -0
- package/skills/fix-ci/SKILL.md +29 -0
- package/skills/fix-merge-conflicts/SKILL.md +32 -0
- package/skills/get-pr-comments/SKILL.md +23 -0
- package/skills/how/SKILL.md +21 -0
- package/skills/in-your-own-words/SKILL.md +7 -0
- package/skills/interrogate/SKILL.md +35 -0
- package/skills/ketchup/SKILL.md +43 -0
- package/skills/ketchup-video/SKILL.md +29 -0
- package/skills/loop-on-ci/SKILL.md +50 -0
- package/skills/maintain-formal-verification-skill/SKILL.md +58 -0
- package/skills/maintain-verification-skill/SKILL.md +39 -0
- package/skills/make-bot-ui/SKILL.md +98 -0
- package/skills/make-pr-easy-to-review/SKILL.md +59 -0
- package/skills/new-branch-and-pr/SKILL.md +29 -0
- package/skills/no-comments/SKILL.md +26 -0
- package/skills/poteto-help/SKILL.md +159 -0
- package/skills/poteto-help/references/prompting.md +51 -0
- package/skills/poteto-help/references/recipes.md +51 -0
- package/skills/poteto-mode/SKILL.md +151 -0
- package/skills/poteto-mode/playbooks/authoring-a-skill.md +12 -0
- package/skills/poteto-mode/playbooks/autonomous-run.md +13 -0
- package/skills/poteto-mode/playbooks/autopilot-full.md +25 -0
- package/skills/poteto-mode/playbooks/autopilot-stack.md +8 -0
- package/skills/poteto-mode/playbooks/babysit.md +23 -0
- package/skills/poteto-mode/playbooks/bug-fix.md +15 -0
- package/skills/poteto-mode/playbooks/eval.md +25 -0
- package/skills/poteto-mode/playbooks/feature.md +21 -0
- package/skills/poteto-mode/playbooks/hillclimb.md +21 -0
- package/skills/poteto-mode/playbooks/investigation.md +14 -0
- package/skills/poteto-mode/playbooks/multi-phase-plan.md +155 -0
- package/skills/poteto-mode/playbooks/opening-a-pr.md +32 -0
- package/skills/poteto-mode/playbooks/orchestrate.md +25 -0
- package/skills/poteto-mode/playbooks/pause-safely.md +10 -0
- package/skills/poteto-mode/playbooks/perf-issue.md +25 -0
- package/skills/poteto-mode/playbooks/prototype.md +14 -0
- package/skills/poteto-mode/playbooks/refactoring.md +16 -0
- package/skills/poteto-mode/playbooks/runtime-forensics.md +11 -0
- package/skills/poteto-mode/playbooks/session-pickup.md +11 -0
- package/skills/poteto-mode/playbooks/shipping.md +12 -0
- package/skills/poteto-mode/playbooks/trace-forensics.md +14 -0
- package/skills/poteto-mode/playbooks/visual-parity.md +11 -0
- package/skills/poteto-mode/playbooks/worktree-cleanup.md +12 -0
- package/skills/poteto-mode/references/bugbot-triage.md +142 -0
- package/skills/poteto-mode/scripts/bootstrap.ts +62 -0
- package/skills/poteto-mode/scripts/bun.lock +67 -0
- package/skills/poteto-mode/scripts/check-plan.mjs +205 -0
- package/skills/poteto-mode/scripts/check-plan.test.ts +110 -0
- package/skills/poteto-mode/scripts/package.json +16 -0
- package/skills/poteto-mode/scripts/watch-pr/cli.test.ts +224 -0
- package/skills/poteto-mode/scripts/watch-pr/cli.ts +223 -0
- package/skills/poteto-mode/scripts/watch-pr/fakes.test-helper.ts +129 -0
- package/skills/poteto-mode/scripts/watch-pr/github.test.ts +498 -0
- package/skills/poteto-mode/scripts/watch-pr/github.ts +726 -0
- package/skills/poteto-mode/scripts/watch-pr/policy.test.ts +482 -0
- package/skills/poteto-mode/scripts/watch-pr/policy.ts +842 -0
- package/skills/poteto-mode/scripts/watch-pr/render.ts +169 -0
- package/skills/poteto-mode/scripts/watch-pr/tsconfig.json +13 -0
- package/skills/poteto-mode/scripts/watch-pr/types.compile.ts +93 -0
- package/skills/poteto-mode/scripts/watch-pr/types.ts +414 -0
- package/skills/poteto-mode/scripts/watch-pr/watch-pr +6 -0
- package/skills/poteto-mode/scripts/worktree-audit.sh +146 -0
- package/skills/pr-review-canvas/SKILL.md +170 -0
- package/skills/pr-review-canvas/renderer.js +170 -0
- package/skills/pr-review-canvas/styles.css +96 -0
- package/skills/pr-review-canvas/template.html +18 -0
- package/skills/principle-attack-the-premise/SKILL.md +21 -0
- package/skills/principle-boundary-discipline/SKILL.md +34 -0
- package/skills/principle-build-the-lever/SKILL.md +23 -0
- package/skills/principle-encode-lessons-in-structure/SKILL.md +11 -0
- package/skills/principle-exhaust-the-design-space/SKILL.md +9 -0
- package/skills/principle-experience-first/SKILL.md +19 -0
- package/skills/principle-explain-the-number/SKILL.md +18 -0
- package/skills/principle-fix-root-causes/SKILL.md +21 -0
- package/skills/principle-foundational-thinking/SKILL.md +21 -0
- package/skills/principle-guard-the-context-window/SKILL.md +12 -0
- package/skills/principle-laziness-protocol/SKILL.md +10 -0
- package/skills/principle-make-operations-idempotent/SKILL.md +22 -0
- package/skills/principle-migrate-callers-then-delete-legacy-apis/SKILL.md +14 -0
- package/skills/principle-minimize-reader-load/SKILL.md +18 -0
- package/skills/principle-model-the-domain/SKILL.md +24 -0
- package/skills/principle-never-block-on-the-human/SKILL.md +15 -0
- package/skills/principle-outcome-oriented-execution/SKILL.md +21 -0
- package/skills/principle-prove-it-works/SKILL.md +22 -0
- package/skills/principle-redesign-from-first-principles/SKILL.md +16 -0
- package/skills/principle-separate-before-serializing-shared-state/SKILL.md +16 -0
- package/skills/principle-sequence-verifiable-units/SKILL.md +17 -0
- package/skills/principle-subtract-before-you-add/SKILL.md +18 -0
- package/skills/principle-test-behavior-not-implementation/SKILL.md +20 -0
- package/skills/principle-type-system-discipline/SKILL.md +13 -0
- package/skills/recall/SKILL.md +37 -0
- package/skills/reflect/SKILL.md +69 -0
- package/skills/reflect/references/divergent-reviewer.md +38 -0
- package/skills/reflect/references/judgment-reviewer.md +37 -0
- package/skills/reflect/references/synthesizer.md +56 -0
- package/skills/reflect/references/tooling-reviewer.md +48 -0
- package/skills/review-and-ship/SKILL.md +41 -0
- package/skills/run-smoke-tests/SKILL.md +42 -0
- package/skills/setup-pstack/SKILL.md +79 -0
- package/skills/sharpen/SKILL.md +16 -0
- package/skills/show-me-your-work/SKILL.md +82 -0
- package/skills/show-me-your-work/references/decision-log-template.tsv +1 -0
- package/skills/show-me-your-work/scripts/log.sh +42 -0
- package/skills/statechart/SKILL.md +82 -0
- package/skills/statechart/references/render.md +93 -0
- package/skills/statechart/scripts/backends/cfg.ts +33 -0
- package/skills/statechart/scripts/backends/mermaid.ts +249 -0
- package/skills/statechart/scripts/backends/plain-text.ts +72 -0
- package/skills/statechart/scripts/backends/report.ts +177 -0
- package/skills/statechart/scripts/frontends/config.ts +276 -0
- package/skills/statechart/scripts/frontends/dot.ts +74 -0
- package/skills/statechart/scripts/frontends/marks.ts +93 -0
- package/skills/statechart/scripts/frontends/messages.ts +52 -0
- package/skills/statechart/scripts/frontends/spec.ts +114 -0
- package/skills/statechart/scripts/frontends/trace.ts +24 -0
- package/skills/statechart/scripts/frontends/value.ts +166 -0
- package/skills/statechart/scripts/frontends/verdict.ts +40 -0
- package/skills/statechart/scripts/frontends/view.ts +119 -0
- package/skills/statechart/scripts/ir.ts +547 -0
- package/skills/statechart/scripts/package.json +11 -0
- package/skills/statechart/scripts/passes/annotate.ts +128 -0
- package/skills/statechart/scripts/passes/label.ts +269 -0
- package/skills/statechart/scripts/passes/lift.ts +85 -0
- package/skills/statechart/scripts/passes/loop-check.ts +68 -0
- package/skills/statechart/scripts/passes/paths.ts +60 -0
- package/skills/statechart/scripts/passes/reach.ts +135 -0
- package/skills/statechart/scripts/passes/region-check.ts +97 -0
- package/skills/statechart/scripts/passes/regions.ts +295 -0
- package/skills/statechart/scripts/pipeline.ts +76 -0
- package/skills/statechart/scripts/run.ts +506 -0
- package/skills/statechart/scripts/statechart +29 -0
- package/skills/statechart/scripts/statechart.ts +164 -0
- package/skills/statechart/scripts/test/ConfigOracle.java +63 -0
- package/skills/statechart/scripts/test/chart.test.ts +1253 -0
- package/skills/statechart/scripts/test/charts/Braces.mmd +7 -0
- package/skills/statechart/scripts/test/charts/Escapes.mmd +11 -0
- package/skills/statechart/scripts/test/charts/Phases.mmd +29 -0
- package/skills/statechart/scripts/test/cli.test.ts +1315 -0
- package/skills/statechart/scripts/test/config-fuzz.test.ts +263 -0
- package/skills/statechart/scripts/test/corpus/Counter/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/Counter/Counter.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/Counter/Counter.tla +10 -0
- package/skills/statechart/scripts/test/corpus/Counter/chart.mmd +9 -0
- package/skills/statechart/scripts/test/corpus/Counter/graph.dot +16 -0
- package/skills/statechart/scripts/test/corpus/Counter/report.md +7 -0
- package/skills/statechart/scripts/test/corpus/Counter/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/Counter/verdict-1.out +49 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/ChartRun.out +60 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/CounterAction.cfg +4 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/CounterAction.tla +22 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/chart.mmd +26 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/graph.dot +19 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/report.md +20 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/verdict-2.out +82 -0
- package/skills/statechart/scripts/test/corpus/CounterAction/verdict-3.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/CounterDeadlock.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/CounterDeadlock.tla +11 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/chart.mmd +22 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/graph.dot +16 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/report.md +17 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-2.out +77 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/ChartRun.out +69 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/CounterFan.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/CounterFan.tla +11 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/chart.mmd +85 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/graph.dot +70 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/report.md +12 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/verdict-1.out +67 -0
- package/skills/statechart/scripts/test/corpus/CounterFan/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/ChartRun.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/ChartRun.out +85 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/CounterGuard.cfg +6 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/CounterGuard.tla +13 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/chart.mmd +5 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/graph.dot +10 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/report.md +31 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/verdict-1.out +64 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterGuard/verdict-2.out +77 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/ChartRun.out +55 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/CounterInitPast.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/CounterInitPast.tla +10 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/chart.mmd +12 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/graph.dot +6 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/report.md +12 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/verdict-1.out +33 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPast/verdict-2.out +54 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/ChartRun.out +54 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/CounterInitPastHolds.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/CounterInitPastHolds.tla +10 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/chart.mmd +1 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/graph.dot +6 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/report.md +7 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterInitPastHolds/verdict-1.out +46 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/CounterInstance.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/CounterInstance.tla +10 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/CounterSteps.tla +6 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/chart.mmd +17 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/graph.dot +15 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/report.md +14 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/sany.out +3 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterInstance/verdict-1.out +78 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/CounterJump.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/CounterJump.tla +19 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/chart.mmd +26 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/graph.dot +22 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/report.md +12 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/verdict-1.out +58 -0
- package/skills/statechart/scripts/test/corpus/CounterJump/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/CounterLoop.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/CounterLoop.tla +11 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/chart.mmd +17 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/graph.dot +15 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/report.md +14 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterLoop/verdict-1.out +76 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/CounterOrder.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/CounterOrder.tla +11 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/chart.mmd +19 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/graph.dot +10 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/report.md +15 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterOrder/verdict-2.out +67 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/ChartRun.out +62 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/CounterRules.cfg +6 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/CounterRules.tla +24 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/Moves.tla +5 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/chart.mmd +22 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/graph.dot +10 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/report.md +23 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/sany.out +3 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-1.out +58 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-2.out +66 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-3.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-3.out +74 -0
- package/skills/statechart/scripts/test/corpus/CounterRules/verdict-4.out +59 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/ChartRun.out +58 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/CounterStart.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/CounterStart.tla +15 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/chart.mmd +18 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/graph.dot +13 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/report.md +11 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/verdict-1.out +33 -0
- package/skills/statechart/scripts/test/corpus/CounterStart/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/CounterStop.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/CounterStop.tla +15 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/chart.mmd +7 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/graph.dot +13 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/report.md +6 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterStop/verdict-1.out +49 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/ChartRun.out +61 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/CounterTie.cfg +4 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/CounterTie.tla +14 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/chart.mmd +30 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/graph.dot +19 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/report.md +27 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-2.out +64 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-3.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-3.out +87 -0
- package/skills/statechart/scripts/test/corpus/CounterTie/verdict-4.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/ChartRun.out +60 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/CounterTieInGraph.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/CounterTieInGraph.tla +12 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/chart.mmd +23 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/graph.dot +19 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/report.md +11 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/CounterTieInGraph/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterView/ChartRun.out +61 -0
- package/skills/statechart/scripts/test/corpus/CounterView/CounterView.cfg +4 -0
- package/skills/statechart/scripts/test/corpus/CounterView/CounterView.tla +14 -0
- package/skills/statechart/scripts/test/corpus/CounterView/chart.mmd +23 -0
- package/skills/statechart/scripts/test/corpus/CounterView/graph.dot +19 -0
- package/skills/statechart/scripts/test/corpus/CounterView/report.md +27 -0
- package/skills/statechart/scripts/test/corpus/CounterView/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-2.out +64 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-3.exit +1 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-3.out +87 -0
- package/skills/statechart/scripts/test/corpus/CounterView/verdict-4.out +57 -0
- package/skills/statechart/scripts/test/corpus/CounterView/view.mjs +1 -0
- package/skills/statechart/scripts/test/corpus/DieHard/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/DieHard/DieHard.cfg +4 -0
- package/skills/statechart/scripts/test/corpus/DieHard/DieHard.tla +38 -0
- package/skills/statechart/scripts/test/corpus/DieHard/chart.mmd +92 -0
- package/skills/statechart/scripts/test/corpus/DieHard/graph.dot +126 -0
- package/skills/statechart/scripts/test/corpus/DieHard/report.md +17 -0
- package/skills/statechart/scripts/test/corpus/DieHard/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/DieHard/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/DieHard/verdict-1.out +91 -0
- package/skills/statechart/scripts/test/corpus/DieHard/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/ChartRun.out +61 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/FirstRule.cfg +6 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/FirstRule.tla +11 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/chart.mmd +22 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/graph.dot +16 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/report.md +25 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-2.out +64 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-3.exit +1 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-3.out +64 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-4.exit +1 -0
- package/skills/statechart/scripts/test/corpus/FirstRule/verdict-4.out +77 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/HiddenClock.cfg +4 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/HiddenClock.tla +11 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/chart.mmd +13 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/graph.dot +12 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/report.md +11 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/HiddenClock/verdict-1.out +72 -0
- package/skills/statechart/scripts/test/corpus/Login/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/Login/Login.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/Login/Login.tla +62 -0
- package/skills/statechart/scripts/test/corpus/Login/chart.mmd +28 -0
- package/skills/statechart/scripts/test/corpus/Login/graph.dot +40 -0
- package/skills/statechart/scripts/test/corpus/Login/report.md +7 -0
- package/skills/statechart/scripts/test/corpus/Login/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/Login/verdict-1.out +47 -0
- package/skills/statechart/scripts/test/corpus/Login/view.mjs +1 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/LoginGuarded.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/LoginGuarded.tla +64 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/chart.mmd +28 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/graph.dot +37 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/report.md +8 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/verdict-1.out +47 -0
- package/skills/statechart/scripts/test/corpus/LoginGuarded/view.mjs +1 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/ChartRun.out +60 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/LoginParallel.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/LoginParallel.tla +64 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/chart.mmd +44 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/graph.dot +58 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/report.md +17 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/verdict-1.out +83 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/LoginParallel/view.mjs +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/ChartRun.out +60 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/MediaPlayer.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/MediaPlayer.tla +103 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/chart.mmd +43 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/graph.dot +93 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/report.md +14 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/verdict-1.out +59 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/verdict-2.out +72 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayer/view.mjs +3 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/MediaPlayerFixed.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/MediaPlayerFixed.tla +100 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/chart.mmd +31 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/graph.dot +85 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/report.md +9 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/verdict-1.out +47 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerFixed/view.mjs +3 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/MediaPlayer.tla +103 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/MediaPlayerProps.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/MediaPlayerProps.tla +6 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/chart.mmd +42 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/graph.dot +93 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/report.md +19 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-1.out +61 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-2.out +59 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-3.out +61 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-4.exit +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-4.out +66 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-5.exit +1 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-5.out +58 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-6.out +49 -0
- package/skills/statechart/scripts/test/corpus/MediaPlayerProps/view.mjs +3 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/PickWorker.cfg +6 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/PickWorker.tla +11 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/chart.mmd +5 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/graph.dot +11 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/report.md +7 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/sany.out +5 -0
- package/skills/statechart/scripts/test/corpus/PickWorker/verdict-1.out +70 -0
- package/skills/statechart/scripts/test/corpus/Shadow/ChartRun.out +61 -0
- package/skills/statechart/scripts/test/corpus/Shadow/Shadow.cfg +4 -0
- package/skills/statechart/scripts/test/corpus/Shadow/Shadow.tla +11 -0
- package/skills/statechart/scripts/test/corpus/Shadow/ShadowLib.tla +6 -0
- package/skills/statechart/scripts/test/corpus/Shadow/ShadowSub.tla +3 -0
- package/skills/statechart/scripts/test/corpus/Shadow/chart.mmd +9 -0
- package/skills/statechart/scripts/test/corpus/Shadow/graph.dot +16 -0
- package/skills/statechart/scripts/test/corpus/Shadow/report.md +8 -0
- package/skills/statechart/scripts/test/corpus/Shadow/sany.out +4 -0
- package/skills/statechart/scripts/test/corpus/Shadow/verdict-1.out +65 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/ChartRun.out +59 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/SpacedNames.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/SpacedNames.tla +9 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/chart.mmd +23 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/graph.dot +17 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/report.md +15 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/verdict-1.out +65 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/SpacedNames/verdict-2.out +75 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/ChartRun.out +69 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/TwoPhase.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/TwoPhase.tla +75 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/chart.mmd +60 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/graph.dot +297 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/report.md +20 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/verdict-1.out +95 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/verdict-2.out +57 -0
- package/skills/statechart/scripts/test/corpus/TwoPhase/view.mjs +1 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/ChartRun.out +57 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/TwoPhaseFixed.cfg +3 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/TwoPhaseFixed.tla +75 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/chart.mmd +37 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/graph.dot +223 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/report.md +11 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/sany.out +1 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/verdict-1.out +47 -0
- package/skills/statechart/scripts/test/corpus/TwoPhaseFixed/view.mjs +1 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/ChartRun.exit +1 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/ChartRun.out +75 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/TypeGuard.cfg +5 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/TypeGuard.tla +11 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/chart.mmd +18 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/graph.dot +14 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/report.md +29 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/verdict-1.out +64 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/TypeGuard/verdict-2.out +75 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/ChartRun.out +58 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/UserNoDeadlock.cfg +2 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/UserNoDeadlock.tla +8 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/chart.mmd +22 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/graph.dot +16 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/report.md +15 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/sany.out +2 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-1.exit +1 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-1.out +56 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-2.exit +1 -0
- package/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-2.out +77 -0
- package/skills/statechart/scripts/test/corpus.test.ts +441 -0
- package/skills/statechart/scripts/test/differential.test.ts +565 -0
- package/skills/statechart/scripts/test/drawn.ts +20 -0
- package/skills/statechart/scripts/test/grid/Grid.cfg +2 -0
- package/skills/statechart/scripts/test/grid/Grid.tla +9 -0
- package/skills/statechart/scripts/test/grid/sany.out +2 -0
- package/skills/statechart/scripts/test/java.ts +63 -0
- package/skills/statechart/scripts/test/labels.ts +648 -0
- package/skills/statechart/scripts/test/messages.test.ts +212 -0
- package/skills/statechart/scripts/test/pipeline.test.ts +270 -0
- package/skills/statechart/scripts/test/plain-tlc.test.ts +255 -0
- package/skills/statechart/scripts/test/render.test.ts +145 -0
- package/skills/statechart/scripts/test/tlc-out.test.ts +90 -0
- package/skills/statechart/scripts/test/tlc.ts +158 -0
- package/skills/statechart/scripts/tsconfig.json +11 -0
- package/skills/statechart/scripts/worker.ts +35 -0
- package/skills/swarm/SKILL.md +41 -0
- package/skills/tdd/SKILL.md +42 -0
- package/skills/teach/SKILL.md +23 -0
- package/skills/technical-writing/SKILL.md +106 -0
- package/skills/thermo-nuclear-code-quality-review/SKILL.md +192 -0
- package/skills/typescript-best-practices/SKILL.md +32 -0
- package/skills/typescript-best-practices/references/patterns.md +328 -0
- package/skills/unslop/SKILL.md +62 -0
- package/skills/verify-this/SKILL.md +74 -0
- package/skills/weekly-review/SKILL.md +32 -0
- package/skills/what-did-i-get-done/SKILL.md +31 -0
- package/skills/why/SKILL.md +9 -0
- package/skills/workflow-from-chats/SKILL.md +50 -0
- package/src/credentials.ts +156 -0
- package/src/index.ts +663 -0
- package/src/jobs.ts +436 -0
- package/src/sandbox.ts +232 -0
- package/src/sweep.ts +132 -0
- package/src/transcript.ts +66 -0
|
@@ -0,0 +1,182 @@
|
|
|
1
|
+
# Recipes and pitfalls
|
|
2
|
+
|
|
3
|
+
Prompts worth copying, then the mistakes everyone makes once. Swap in your own paths and finish conditions. The recipes are deliberately informal. That's how they get typed in practice, and the skills read intent fine.
|
|
4
|
+
|
|
5
|
+

|
|
6
|
+
|
|
7
|
+
## Understand an unfamiliar subsystem
|
|
8
|
+
|
|
9
|
+
```text
|
|
10
|
+
use /skill:how first to understand how this initialization works. then use /skill:why to figure out why it broke recently.
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
Mechanics first, history second. Each skill's report tells you which sources it searched, so you know what the answer is grounded in.
|
|
14
|
+
|
|
15
|
+
## Restate a noisy report before touching code
|
|
16
|
+
|
|
17
|
+
```text
|
|
18
|
+
/skill:poteto-mode read this thread. restate the underlying issue in your own words, in plain english. don't change any code yet.
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
A misreading shows up in the restatement, where it costs one message to correct. Keep your own theory to yourself until the agent has stated its own. `/skill:in-your-own-words` asks for the restatement alone, with no playbook.
|
|
22
|
+
|
|
23
|
+
## Sharpen a prompt before you send it
|
|
24
|
+
|
|
25
|
+
```text
|
|
26
|
+
/skill:sharpen write the onboarding doc for the new billing service.
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
The agent names what an expert would do that you didn't ask for, the raw material they'd start from, their methods and tools, and an outside check that the result is right. It hands back your prompt rewritten to ask for that and doesn't do the task. Send the rewrite when it reads right.
|
|
30
|
+
|
|
31
|
+
## Prototype before you pick
|
|
32
|
+
|
|
33
|
+
```text
|
|
34
|
+
/skill:poteto-mode prototype a few options for the settings layout. put them behind a switcher and send me screenshots of each.
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
You pick from things that run, not from descriptions. The agent answers its own layout and timing questions along the way.
|
|
38
|
+
|
|
39
|
+
## Turn a settled design into a plan
|
|
40
|
+
|
|
41
|
+
```text
|
|
42
|
+
/skill:poteto-mode turn this design into a plan. small verifiable PRs, each with its own proof.
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
Ask only after the design settles. The plan is the deliverable, and it names the playbook that will execute it.
|
|
46
|
+
|
|
47
|
+
## Get a second opinion on a design
|
|
48
|
+
|
|
49
|
+
```text
|
|
50
|
+
ask /skill:arena for a second opinion on this thread and our approach
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
Your current design becomes one candidate among several, and the synthesis tells you whether the panel found something better or confirmed what you had. It costs little next to a design that is expensive to reverse.
|
|
54
|
+
|
|
55
|
+
## Check independent slices in parallel
|
|
56
|
+
|
|
57
|
+
```text
|
|
58
|
+
/skill:swarm check every package under packages/ against its check.sh. one worker per package. one report.
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
Each worker owns one package. The parent waits for every slice and returns one `PASS`, `ISSUES`, or `BLOCKED` report instead of raw worker dumps.
|
|
62
|
+
|
|
63
|
+
## Review a branch skeptically
|
|
64
|
+
|
|
65
|
+
```text
|
|
66
|
+
/skill:interrogate the whole branch, but skeptically. don't change anything yet. no nitpicks unless it's an actual bug or regression in behavior.
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
The qualifiers do real work. "don't change anything yet" keeps it read-only, and the nitpick rule pre-filters the noise so the verified findings are worth your time.
|
|
70
|
+
|
|
71
|
+
## Fix a bug through a failing test
|
|
72
|
+
|
|
73
|
+
```text
|
|
74
|
+
/skill:poteto-mode repro the duplicate write first. if there's a cheap test path, /skill:tdd it. then fix and rerun.
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
"if there's a cheap test path" matters. Forcing a test through brittle mocks proves less than running the real command, and the playbook is allowed to say so.
|
|
78
|
+
|
|
79
|
+
## Repro and fix a report with proof
|
|
80
|
+
|
|
81
|
+
```text
|
|
82
|
+
/skill:poteto-mode repro this with /skill:verify-<app>. if it repros on main, fix it and show me a video as proof.
|
|
83
|
+
```
|
|
84
|
+
|
|
85
|
+
"if it repros on main" lets the run stop early when the bug is already gone. The video lets you check the fix before you read the diff.
|
|
86
|
+
|
|
87
|
+
## Prove a property tests rarely reach
|
|
88
|
+
|
|
89
|
+
```text
|
|
90
|
+
/skill:create-formal-verification-skill the retry queue. a message must never be delivered twice.
|
|
91
|
+
```
|
|
92
|
+
|
|
93
|
+
You get one property checked in every case within a stated scope, a counterexample in your code's terms if the code already breaks it, and a project skill the next agent runs on any change to that code.
|
|
94
|
+
|
|
95
|
+
## Vet a number before you post it
|
|
96
|
+
|
|
97
|
+
```text
|
|
98
|
+
/skill:benchmark-checklist vet this 40% speedup before it goes in the pr description
|
|
99
|
+
```
|
|
100
|
+
|
|
101
|
+
You get faster, slower, no measurable difference, or inconclusive, with the run count, the range, and what limits the number.
|
|
102
|
+
|
|
103
|
+
## Stop correcting the same mistake
|
|
104
|
+
|
|
105
|
+
```text
|
|
106
|
+
/skill:correct agents keep adding new config flags without registering them in the schema
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
The fix lands in the repo as architecture, a type, a lint, or a test, so the next agent can't make the mistake.
|
|
110
|
+
|
|
111
|
+
## Ask how without starting the work
|
|
112
|
+
|
|
113
|
+
```text
|
|
114
|
+
/skill:poteto-help how do i get poteto-mode to stay on every turn?
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
You get an answer, a prompt to send, and a link to the source. Nothing runs until you send that prompt.
|
|
118
|
+
|
|
119
|
+
## Keep a run honest while you're away
|
|
120
|
+
|
|
121
|
+
```text
|
|
122
|
+
im going to bed, keep going autonomously until every fixture passes. do not stop. keep a decision log i can audit in the morning.
|
|
123
|
+
```
|
|
124
|
+
|
|
125
|
+
The full contract is on the [overnight page](./07-overnight.md). The short form works once the task and finish condition are already in the conversation.
|
|
126
|
+
|
|
127
|
+
## Redirect a drifting run
|
|
128
|
+
|
|
129
|
+
Steering prompts are one line:
|
|
130
|
+
|
|
131
|
+
```text
|
|
132
|
+
i said the goal is to repro. i did not ask for a fix yet.
|
|
133
|
+
```
|
|
134
|
+
|
|
135
|
+
```text
|
|
136
|
+
apply prove it works. show me the real output, not the build log.
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
```text
|
|
140
|
+
/skill:unslop that, no emdashes
|
|
141
|
+
```
|
|
142
|
+
|
|
143
|
+
You rarely need more words. You need the right name, and [the principles page](./08-principles.md) is the vocabulary.
|
|
144
|
+
|
|
145
|
+
## Get the reply in plain words
|
|
146
|
+
|
|
147
|
+
```text
|
|
148
|
+
/skill:bro
|
|
149
|
+
```
|
|
150
|
+
|
|
151
|
+
That's the whole prompt. [`/skill:bro`](../../skills/bro/SKILL.md) restates the last message like one human talking to another, no jargon, shorter. Use it when a reply is technically thorough and you still don't know what it said.
|
|
152
|
+
|
|
153
|
+
## Catch up on a chat you left running
|
|
154
|
+
|
|
155
|
+
```text
|
|
156
|
+
/skill:ketchup
|
|
157
|
+
```
|
|
158
|
+
|
|
159
|
+
[`/skill:ketchup`](../../skills/ketchup/SKILL.md) tells you in plain words what changed since your last message, then lists each call waiting on you with its pick, evidence, and risk. It changes nothing while it reports.
|
|
160
|
+
|
|
161
|
+
To watch the catch-up instead, run [`/skill:ketchup-video`](../../skills/ketchup-video/SKILL.md). It shows what happened in a short subtitled video of slides, and lists the calls waiting on you as text under it.
|
|
162
|
+
|
|
163
|
+
## The pitfalls
|
|
164
|
+
|
|
165
|
+
- **Enumerating skills in the prompt.** "use /skill:architect then /skill:arena then /skill:interrogate" reorders steps the playbook already sequences. State the goal and constraints. Name a skill only to override a default.
|
|
166
|
+
- **A vague finish condition.** "make it better" gives a heartbeat nothing to check. Give a command or artifact that can pass or fail.
|
|
167
|
+
- **Leading with your theory of the cause.** The agent searches wherever you pointed. Ask it to restate the problem first, then share your hunch.
|
|
168
|
+
- **Taking the first design.** One attempt locks in the first shape the model thought of. Ask for prototypes or `/skill:architect` and pick from evidence.
|
|
169
|
+
- **Polishing an abstract plan.** Adversarial review of a plan with no code behind it invents risks that will never happen. Settle the open questions with prototypes, then review what got built.
|
|
170
|
+
- **Parallel agents in one worktree.** They overwrite each other, and nobody can tell which agent changed what. Spawn each with its own `worktree`, or say "own worktree per attempt".
|
|
171
|
+
- **Looping before you trust the loop.** A loop that can't verify its own work only makes unchecked work faster. Get the verification skill working first.
|
|
172
|
+
- **Trusting an unvetted number.** A warm cache or a skipped code path can fake a speedup. Run `/skill:benchmark-checklist` before the number goes anywhere.
|
|
173
|
+
- **Correcting the same mistake by hand.** A correction in chat helps one run. `/skill:correct` fixes the repo so no later run repeats it.
|
|
174
|
+
- **Using `/skill:arena` for coverage.** `/skill:arena` repeats one design or code brief, then picks a base and grafts the best parts. `/skill:swarm` partitions slices or declared race arms and aggregates one report.
|
|
175
|
+
- **Accepting every review comment.** Bots and humans both file real catches and noise in one list. `/skill:interrogate` keeps only the findings a rerun proves and lists what it dropped and why, and you can override either way.
|
|
176
|
+
- **Treating `auto` as a model.** `auto` and `inherit-parent` mean "omit the model so the spawned Pi runs on your session model." [Setup](./01-setup.md) covers the roles.
|
|
177
|
+
- **Reporting success off a green build.** A build proves it compiles. Ask for the real command, flow, stored value, or profile, and expect the evidence in the reply.
|
|
178
|
+
- **Writing a `SKILL.md` freehand.** Route it through the [Authoring or modifying a skill playbook](../../skills/poteto-mode/playbooks/authoring-a-skill.md) so validation and review happen.
|
|
179
|
+
|
|
180
|
+
That's the guide. If you skipped ahead, go back to [setup](./01-setup.md) and run one real task. The habits stick from use, not from reading.
|
|
181
|
+
|
|
182
|
+
Back to the [guide index](./README.md).
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
# The pstack guide
|
|
2
|
+
|
|
3
|
+
pstack works best when you stop micromanaging the agent. You describe what you want and how you'll know it's done. `/skill:poteto-mode` picks the playbook, runs the other skills as the steps need them, and shows you the evidence. This guide teaches that habit with realistic prompts.
|
|
4
|
+
|
|
5
|
+
Here's what you'll learn:
|
|
6
|
+
|
|
7
|
+
1. [Set up pstack](./01-setup.md). Install the package and pick your models.
|
|
8
|
+
2. [Route work through `/skill:poteto-mode`](./02-poteto-mode.md). Give it a goal and watch it pick a playbook.
|
|
9
|
+
3. [Understand the code](./03-understand.md). A read-only investigation, then `/skill:how`, `/skill:why`, `/skill:teach`, and `/skill:recall` before you edit anything.
|
|
10
|
+
4. [Design the change](./04-design.md). `/skill:architect`, `/skill:arena`, `/skill:swarm`, `/skill:interrogate`, prototypes, and plans before code locks in a shape.
|
|
11
|
+
5. [Build and clean the change](./05-build-and-clean.md). The build playbooks, `/skill:tdd`, `/skill:unslop`, and `/skill:no-comments`.
|
|
12
|
+
6. [Verify and ship](./06-verify-and-ship.md). Prove behavior on the real app, formally verify what tests rarely reach, vet numbers with `/skill:benchmark-checklist`, then open a focused PR and drive it to merged.
|
|
13
|
+
7. [Run work while you sleep](./07-overnight.md). Trust before loops, an overnight contract, a decision log you can audit, and coordinators and scheduled runs that scale past one session.
|
|
14
|
+
8. [Steer with principle names](./08-principles.md). The 24 names that redirect an agent mid-task.
|
|
15
|
+
9. [Make it yours](./09-make-it-yours.md). Your own mode, `/skill:correct` for repeated mistakes, and how to test a skill change.
|
|
16
|
+
10. [Recipes and pitfalls](./10-recipes-and-pitfalls.md). Prompts to copy and mistakes to skip.
|
|
17
|
+
|
|
18
|
+
Read the pages in order the first time. After that, each page stands alone.
|
|
19
|
+
|
|
20
|
+
When you're stuck, or can't tell which skill fits, type [`/skill:poteto-help`](../../skills/poteto-help/SKILL.md) with your question:
|
|
21
|
+
|
|
22
|
+
```text
|
|
23
|
+
/skill:poteto-help which skill should i use to review this branch?
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
It answers, hands you a prompt to send, and links the skill or guide page the answer came from. It doesn't start the work, because a pstack run spends real tokens, so you send the prompt when you're ready. It runs only when you type it.
|
|
27
|
+
|
|
28
|
+
## If you only remember one thing
|
|
29
|
+
|
|
30
|
+
Give the agent a goal and a way to check it, in your own words:
|
|
31
|
+
|
|
32
|
+
```text
|
|
33
|
+
/skill:poteto-mode the export writes duplicate rows when a retry lands mid-run. repro first, then fix and verify.
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
You don't need to name a playbook or list skills. "repro first" and a checkable outcome are all the routing signal `/skill:poteto-mode` needs. It matches the Bug fix playbook, copies the steps into `TODO.md`, and calls the right skills as each step fires.
|
|
37
|
+
|
|
38
|
+
Next: [Set up pstack](./01-setup.md).
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
# How pstack maps onto Pi
|
|
2
|
+
|
|
3
|
+
pstack 0.15.42 and cursor-team-kit 1.2.0 were written for Cursor. `upstream.lock.json` pins the exact upstream commit. This package keeps every skill, playbook, principle, agent, rule, script, and guide chapter, and replaces each Cursor or Claude Code mechanism with the Pi mechanism that does the same job. The skills name Pi mechanisms directly. There is no adapter to read at run time.
|
|
4
|
+
|
|
5
|
+
Pi skips sub-agents, permission popups, plan mode, built-in to-dos, and background bash on purpose. Each row below names what pstack does instead.
|
|
6
|
+
|
|
7
|
+
## Pi's rules this port follows
|
|
8
|
+
|
|
9
|
+
| Pi rule | What pstack does |
|
|
10
|
+
| --- | --- |
|
|
11
|
+
| No sub-agents. Spawn Pi instances via tmux. | `pi_spawn` starts a separate `pi -p` process in its own tmux session with a standalone brief. It runs in parallel and wakes the spawning session with its report when it exits. |
|
|
12
|
+
| No permission popups. Run in a container. | Every `pi_spawn` and `tmux_run` job runs inside Seatbelt (`sandbox-exec`) on macOS or bubblewrap (`bwrap`) on Linux and WSL2. Writes are limited to the worker's own session directory, its worktree or working directory, the repository's git directory, and temp directories. Pi's own configuration stays read-only. No job runs unsandboxed. |
|
|
13
|
+
| No plan mode. Write plans to files. | A plan is a Markdown file, such as `plans/<slug>.md`. The human reviews the file. |
|
|
14
|
+
| No built-in to-dos. Use a TODO.md file. | Each checklist pstack used to keep in a todo tool lives in `TODO.md` at the root of the checkout you work in, as `- [ ]` and `- [x]` lines. It is working state, so never stage it. When the checkout already tracks a `TODO.md`, the checklist is `.pi/TODO.md`. |
|
|
15
|
+
| No background bash. Use tmux. Full observability, direct interaction. | Watchers, dev servers, long builds, and heartbeat ticks run through `tmux_run`. Nothing uses `&`, `nohup`, `setsid`, or `disown`. Every job is a tmux session you can attach to with the command `tmux_jobs` `list` prints. Its output shows there as it is written, and Ctrl-C there stops it. A job reads no input, so a command that needs an answer typed runs in the root session. |
|
|
16
|
+
|
|
17
|
+
Pi's design principle for customizing is to pick the least powerful mechanism that meets the need. Skills carry all workflow text. The one extension (`src/index.ts`) exists only for what a skill cannot do: start sandboxed tmux jobs, wake the session when they exit, and put the model-role lines and the two team-kit rules into the system prompt.
|
|
18
|
+
|
|
19
|
+
## Vocabulary
|
|
20
|
+
|
|
21
|
+
| Cursor or Claude Code | Pi |
|
|
22
|
+
| --- | --- |
|
|
23
|
+
| Subagent, `Task` call, delegate, worker | A Pi instance started with `pi_spawn`. Call it a worker, a spawned Pi, or by its role (explorer, reviewer, runner). Never call it a subagent. |
|
|
24
|
+
| `subagent_type: "poteto-agent"`, `"comment-sicko"`, `"ci-watcher"`, `"thermo-nuclear-code-quality-review"` | `pi_spawn` with `agent: "<name>"`. The role text comes from `agents/<name>.md`. |
|
|
25
|
+
| `subagent_type: generalPurpose`, `"shell"`, `"explore"` | `pi_spawn` with no `agent`. |
|
|
26
|
+
| `readonly: true` (Ask mode) | `pi_spawn` with `readonly: true`. The sandbox denies writes outside the job directory and the edit and write tools are removed. MCP stays available, so a reviewer that needs MCP can still be readonly. |
|
|
27
|
+
| `readonly: false` (agent mode) | Leave `readonly` unset. |
|
|
28
|
+
| `environment: "cloud"`, Cursor cloud agent, `cloud_base_branch` | `pi_spawn` with `worktree: "<branch>"` and `base: "<ref>"`. The worker gets its own git worktree, and the sandbox confines its writes there. Cursor cloud agents start from the repository's default branch. A worktree here starts from the session's current `HEAD` unless `base` names another ref, so pass the default branch as `base` to start from it. |
|
|
29
|
+
| `environment: "local"` | Omit `worktree`. |
|
|
30
|
+
| `run_in_background: true` | Nothing to set. Every `pi_spawn` runs in parallel, and you are woken when it exits. Keep working or end your turn. |
|
|
31
|
+
| Spawn N in one message | N `pi_spawn` calls in one message. |
|
|
32
|
+
| Nested subagents, launched by a subagent | The same limit as Cursor. The root Pi and the workers it starts have `pi_spawn`. A worker started by another worker does not, and the root refuses a Pi request from one. Every worker keeps `tmux_run` and `tmux_jobs`. |
|
|
33
|
+
| `resume` an agent | `pi_spawn` with `resume: "<job id>"` continues that job's Pi session. |
|
|
34
|
+
| Steer or stop a running agent | `tmux_jobs` with `action: "stop"`, then a fresh `pi_spawn` with consolidated scope. A print-mode Pi takes no mid-run input. |
|
|
35
|
+
| Wait for agents | End your turn and let the wake arrive. `tmux_jobs` `wait` is for a short wait on named jobs. A spawned Pi running in print mode waits for its own jobs automatically before it finishes. |
|
|
36
|
+
| `file_attachments` | List the paths in the brief. |
|
|
37
|
+
| `model` slug such as `claude-opus-5-5-xhigh` or `grok-4.7-xhigh-fast` | `pi_spawn` `model: "<provider>/<id>"` and `thinking: "<level>"`. Thinking levels are `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`. Pi has no fast variant, so a "fast" choice is dropped. |
|
|
38
|
+
| `~/.cursor/rules/pstack-models.mdc`, `~/.claude/rules/pstack-models.md` | `~/.pi/agent/pstack-v2-models.md`, written by `/skill:setup-pstack`. The extension shows its role lines to the model in a `pstack-models` system-prompt section. A role with no line, or a line of `inherit-parent` or `auto`, runs on the session model, so omit `model`. |
|
|
39
|
+
| A model slug the Task tool rejects | A model `pi_spawn` rejects. It accepts only `provider/id` values that `pi --list-models` prints. |
|
|
40
|
+
| Open a todolist, `TodoWrite` | Write `TODO.md`. |
|
|
41
|
+
| `AskQuestion` (multiple-choice popup) | Ask in plain text with numbered options, then end your turn. Pi has no question popups. |
|
|
42
|
+
| `/loop` with an event | `tmux_run` the watcher command with `wake: "<what to do next>"`. |
|
|
43
|
+
| `/loop <interval>` heartbeat | `tmux_run` with `command: "sleep <seconds>"`, `wake: "<tick prompt>"`, and `repeat: true`. Stop it with `tmux_jobs` `stop`. |
|
|
44
|
+
| A shell command run in the background | `tmux_run`. |
|
|
45
|
+
| Plan mode, a plan to approve | A plan file. |
|
|
46
|
+
| `/<skill>` | `/skill:<skill>`. |
|
|
47
|
+
| A skill that says to run another skill by name | Pi hides skills marked `disable-model-invocation` from the skill list. The extension adds one system-prompt line giving the absolute path of the package's `skills/` directory. The model reads `<dir>/<name>/SKILL.md` and follows it. |
|
|
48
|
+
| `.cursor/skills/`, `~/.cursor/skills/` | `.pi/skills/`, `~/.pi/agent/skills/`, or the Agent Skills paths `.agents/skills/` and `~/.agents/skills/`. |
|
|
49
|
+
| `.cursor/rules/*.mdc`, always-applied rules | `AGENTS.md` (project) or `~/.pi/agent/AGENTS.md` (user). |
|
|
50
|
+
| `~/.cursor/plugins/`, `.cursor-plugin/plugin.json`, `/add-plugin` | A Pi package: `pi install <source>`, listed by `pi list`. |
|
|
51
|
+
| Cursor chat transcripts in `~/.cursor/projects/<slug>/agent-transcripts/` | Pi sessions in `~/.pi/agent/sessions/--<cwd with / as ->--/*.jsonl`. Spawned workers keep theirs in `~/.pi/agent/pstack-v2/jobs/<id>/session/`. The extension names the current session's file in a `pstack-session` system-prompt section, and a brief that asks a worker to read it carries that path, because a worker's agent directory is its job's own. |
|
|
52
|
+
| `/create-skill` | Write `SKILL.md` to Pi's skills spec (Agent Skills format) and check it loads with `/skill:<name>`. |
|
|
53
|
+
| Cursor Automations, routines, webhook wakes, `SendToUser` | A tmux job that runs `pi -p` against a session, or Pi's RPC mode. Secrets come from environment variables the user sets, never from chat. |
|
|
54
|
+
| Cursor canvas | A self-contained HTML file opened in the browser. |
|
|
55
|
+
| Cursor Bugbot, agentic security review | Unchanged. They are GitHub reviewers whose comments any harness reads from the forge. |
|
|
56
|
+
| Cursor's built-in PR tool | `gh`. |
|
|
57
|
+
| MCP tools | Pi's built-in MCP (`pi mcp list`, `~/.pi/agent/mcp.json`, `.pi/mcp.json`) and Codemode (`"defaultTools": ["+codemode"]` in settings). Workers get a copy of your settings, so they have the same MCP servers and Codemode. |
|
|
58
|
+
| Cursor's agent store, project store, project tracker | Files in the checkout: `decisions.tsv` and `plans/`. A worker keeps its `decisions.tsv` in its worktree, which the root reads at `<agent dir>/pstack-v2/jobs/<id>/worktree/`. |
|
|
59
|
+
| Orchestrate's `notes.md` | A file at the checkout root, never staged, like `TODO.md`. |
|
|
60
|
+
| Origin (`origin pr`) | Kept as is when `command -v origin` succeeds and Origin resolves the repository, otherwise `gh`. Graphite is never required. |
|
|
61
|
+
| Hold or stand-down order to running agents | `tmux_jobs` `stop` after each worker commits a `wip:` checkpoint, then a fresh `pi_spawn` to release. |
|
|
62
|
+
| A lane that needs a simulator, `open`, a local display or socket, or auth that exists only on this machine | Run it in the root session, which is not sandboxed. |
|
|
63
|
+
|
|
64
|
+
## Sandbox details
|
|
65
|
+
|
|
66
|
+
- macOS uses a Seatbelt profile. Linux and WSL2 use bubblewrap. With neither available, `pi_spawn` and `tmux_run` refuse to start.
|
|
67
|
+
- A job writes only its working directory or worktree, that checkout's git directory, its own private temp directory, and for Pi workers its own `session/` and `nested/` directories. Every other write is denied.
|
|
68
|
+
- Both sandboxes enforce the same rules, and `test/parity.test.ts` runs one table of operations inside a real job on each platform and fails on any difference beyond the Linux exceptions listed below.
|
|
69
|
+
- A job cannot add or change a git worktree or submodule, apart from the metadata of the worktree it works in, and cannot write the git directory of a nested repository. A job that needs another revision beside its own exports it into its private temp directory with `git archive <sha> | tar -x -C "$TMPDIR/<name>"`.
|
|
70
|
+
- bubblewrap can make only existing paths read-only, so before a job starts the root creates any missing `hooks/`, `info/`, `worktrees/`, and `modules/` directory and `config.worktree` file in the git directory, empty, on every platform. Git reads them as nothing.
|
|
71
|
+
- Shared temp directories and user caches are not writable, because unsandboxed programs load code cached there, such as Pi's compiled-extension cache. Each job's `TMPDIR`, `XDG_CACHE_HOME`, and npm, bun, pip, uv, Go, Yarn, and Deno caches point at its private temp directory, so installs and builds still work. Those caches are deleted when the job exits, and the rest of its temp directory is kept for the report. Chromium follows `MAC_CHROMIUM_TMPDIR` and zsh follows `TMPPREFIX`, both set to the same directory. On macOS a job finds a `mktemp` first on `PATH` that uses `$TMPDIR`, since the system one prefers the per-user temp directory. A command a worker starts shares the worker's temp directory. On Linux the job also gets a private `/tmp`.
|
|
72
|
+
- `cwd` must be inside the session's project, which is the git top level or else the session cwd, or a linked worktree of the same repository. A checkout of another repository is refused even when it sits inside the project, since the job would be handed that repository's git directory. No writable path may contain Pi's agent directory. The model cannot widen its own sandbox by naming another directory.
|
|
73
|
+
- Paths an unsandboxed process later executes from stay read-only even inside a writable checkout. Those are the git `hooks/`, `config`, `config.worktree`, and `info/` entries, a configured `core.hooksPath`, and the code entries of every `.pi` directory in the checkout at any depth: `extensions`, `settings.json`, `mcp.json`, and installed packages in `npm` and `git`. Git finds hooks through `.git`, every `.git` pointer file such as a submodule's, every linked worktree's `commondir`, `gitdir`, and `config.worktree`, and submodule git directories, so all of those stay read-only. Every existing directory above a protected path, and `.git` itself, cannot be renamed or replaced. A protected path that is a symlink is guarded at the link as well as its target.
|
|
74
|
+
- Code can still appear where none was at launch, because a job can rename a directory it built into place or link a parent elsewhere, and bubblewrap cannot bind what does not exist. At launch the root records every protected path, `.pi` code entry, and `.git` entry in the checkout. When the job exits or is stopped, the unsandboxed wrapper sweeps the checkout and moves anything new of those kinds into the job's `quarantine/` directory, and the job's output says so. The sweep never follows a link, and a `.pi` symlink you already had is left alone. Moving, not deleting, keeps a file you created yourself during the job recoverable. On macOS, Seatbelt also denies writing those paths anywhere in the checkout.
|
|
75
|
+
- Jobs never write your Pi agent directory, your `auth.json` included. Each top-level job gets its own agent directory, through Pi's `PI_CODING_AGENT_DIR`, shared by every job it starts. It links to your configuration, holds `settings.json` with its local package paths anchored to your real agent directory, and holds a copy of your credentials. In it a job may write only the contents of that copy and Pi's lock directories, so no job can change what another job's Pi loads. On Linux it is a throwaway tmpfs view, so other writes there vanish with the job.
|
|
76
|
+
- Pi runs an `auth.json` key that starts with `!` as a command, so the credentials copy holds no command. For a worker's own provider, the root resolves the command once when it starts the worker and puts the resulting key in the copy. Every two seconds, and once more after a job ends, the root carries refreshed OAuth tokens between your `auth.json` and each copy, the later expiry winning, under Pi's lock on both. Only OAuth tokens move, so nothing a job writes as a key or a command reaches your `auth.json`, and a provider you logged out of is never brought back.
|
|
77
|
+
- A job cannot reach the services that would start a process for it. It can neither connect to nor serve a Unix socket, so every tmux server, Docker's socket, the session bus, and every other local service are out of reach. Socket pairs, which child processes use for pipes, still work. macOS denies binding and connecting Unix sockets apart from DNS's, and Linux refuses opening one through a seccomp filter, which also refuses io_uring. On macOS it also cannot use LaunchServices (`open`), Apple Events, launchd, or preference writes, and it can signal only processes in its own sandbox. On Linux `/run` and the user's runtime directory are hidden, and the job runs in its own PID namespace.
|
|
78
|
+
- When a job exits, its whole process group is killed before cleanup, so no child it left behind acts after cleanup. Stopping a job sends TERM, then KILL after three seconds. On Linux every process in its PID namespace dies with it.
|
|
79
|
+
- A Pi worker's own jobs get their own sandbox, so `readonly` holds at any depth, and a resumed worker keeps its `readonly`. On every platform a sandboxed worker writes the job as a request in its `nested/` directory, and the root Pi launches it under a profile built from the paths it validated. The root refuses any request that would write, or run, outside what it granted the top-level worker, so no worker can hand a descendant more than it was given. The root writes results only under the top-level job, never into a worker's directory, and serves requests while it runs. If you quit the root Pi, nested requests wait until you resume that session.
|
|
80
|
+
- Start the main session sandboxed too when you want it contained. For example, run Pi inside one of the methods in Pi's containerization guide.
|
|
81
|
+
|
|
82
|
+
## What the sandbox does not cover
|
|
83
|
+
|
|
84
|
+
- Reads and network access stay open, so a job can read anything you can and send it over the network.
|
|
85
|
+
- A writer job's changes are code you and the root Pi later run, such as tests, builds, package scripts, Makefiles, `.envrc`, a nested repository with its own `.git`, and instruction files such as `AGENTS.md` and `.pi/skills`. Review a worker's diff before you run or trust it, as with any agent.
|
|
86
|
+
- A worker can use a provider whose credential is a `!command` only when that provider is its own model's, since the root resolves only that one. Set a key or log in with OAuth for any other provider a worker needs.
|
|
87
|
+
- On Linux a job can create a `.pi` code entry or a `.git` entry where none existed at launch, since bubblewrap binds only paths that exist and neither Landlock nor seccomp can refuse one name inside a writable directory. macOS denies these while the job runs. On both, the sweep moves them out when the job ends.
|
|
88
|
+
- On Linux a job can add new files to its own agent directory, since Pi takes its locks there as new directories and bubblewrap cannot admit only names ending in `.lock`. That directory is a private copy in memory, so the files vanish when the job ends and no other job or the root sees them. macOS denies them.
|
|
89
|
+
- On Linux a job takes Pi's credential lock in its own throwaway view, so a job refreshing a token and the root syncing that copy at the same moment can lose that refresh. pstack refreshes a worker's credentials just before starting it, so this needs a worker to outlive its token.
|
|
90
|
+
- A job can leave a fake rebase in progress in the git directory, whose steps run if you then run `git rebase --continue`.
|
|
91
|
+
- A print-mode run waits for every job it started with a wake message, so one that never exits keeps it running.
|
|
92
|
+
- On macOS a job cannot run `ps` or `top`, so it reads the load with `uptime`. A bash here-document fails in a checkout the job cannot write, such as a readonly worker's, so the job changes to `$TMPDIR` first or writes with `printf`.
|
|
93
|
+
- Cargo and Maven caches are not redirected to the job's private temp directory, so their downloads fail inside a job.
|
|
94
|
+
- Until a job exits, a protected path it created by rename or link still exists, and an unsandboxed process started in that checkout during the job could use it.
|
|
95
|
+
- On macOS a job process that detaches into its own session with `setsid` survives `stop` and keeps its sandbox rights, still inside its sandbox. It can keep writing what the job could write, including a protected path after cleanup ran. The credential check still reverts any command key it plants. Linux has no such gap, because the PID namespace ends every process.
|
|
96
|
+
- A job can hold the lock on its credentials copy, which pauses token sync for that job until it ends.
|
|
97
|
+
- A job's agent directory is read-only apart from its credentials copy and locks, so Pi state a worker would write there does not persist from a worker. That covers an MCP OAuth refresh in `mcp-auth.json`, a model catalog refresh, and package installs. An OAuth MCP server may need a login from the root session first, since a worker cannot save a refreshed token.
|
|
98
|
+
|
|
99
|
+
## Jobs on disk
|
|
100
|
+
|
|
101
|
+
Each job lives in `~/.pi/agent/pstack-v2/jobs/<id>/`: `job.json` (the spec), `brief.md`, `wrapper.sh`, `inventory.json`, `output.log`, `exit`, its private `tmp/`, a top-level job's `agent/`, any `quarantine/`, and for Pi workers `session/`, `nested/`, and `stderr.log`. The job directory is read-only to the job, so a job cannot rewrite its own spec or exit code. The unsandboxed tmux wrapper writes `output.log` and `exit`. A Pi worker can write only `session/` and `nested/`, and the jobs it starts live in `nested/`. Each spawning session runs its own tmux server on a socket in `/tmp/pstack-v2-<uid>/`, named from a hash of the session id. `tmux_jobs` `list` prints a `tail -f` command to follow each job's output and a `tmux attach` command for each running job. A worker's report is every answer it completed, read from its session file, so a reply to a late job notice cannot replace it. A wake is claimed once through a `woken` marker file, so restarting Pi never delivers a report twice.
|
package/package.json
CHANGED
|
@@ -1,6 +1,51 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@justjoshn/pi-pstack-v2",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"
|
|
5
|
-
"
|
|
6
|
-
|
|
3
|
+
"version": "0.1.1",
|
|
4
|
+
"description": "Use the pstack skills and workflow in Pi, with sandboxed Pi workers and shell jobs running in tmux.",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"license": "MIT",
|
|
7
|
+
"repository": {
|
|
8
|
+
"type": "git",
|
|
9
|
+
"url": "git+https://github.com/just-joshn/pi-customizations.git",
|
|
10
|
+
"directory": "extensions/pi-pstack-v2"
|
|
11
|
+
},
|
|
12
|
+
"keywords": [
|
|
13
|
+
"pi-package",
|
|
14
|
+
"pstack",
|
|
15
|
+
"poteto-mode"
|
|
16
|
+
],
|
|
17
|
+
"engines": {
|
|
18
|
+
"node": ">=22.19.0"
|
|
19
|
+
},
|
|
20
|
+
"files": [
|
|
21
|
+
"src",
|
|
22
|
+
"skills",
|
|
23
|
+
"agents",
|
|
24
|
+
"rules",
|
|
25
|
+
"docs",
|
|
26
|
+
"README.md",
|
|
27
|
+
"LICENSE"
|
|
28
|
+
],
|
|
29
|
+
"pi": {
|
|
30
|
+
"extensions": [
|
|
31
|
+
"./src/index.ts"
|
|
32
|
+
],
|
|
33
|
+
"skills": [
|
|
34
|
+
"./skills"
|
|
35
|
+
]
|
|
36
|
+
},
|
|
37
|
+
"scripts": {
|
|
38
|
+
"test": "vitest run --coverage && bun test skills/poteto-mode/scripts/check-plan.test.ts",
|
|
39
|
+
"typecheck": "tsc --noEmit -p tsconfig.json"
|
|
40
|
+
},
|
|
41
|
+
"peerDependencies": {
|
|
42
|
+
"@earendil-works/pi-coding-agent": "*",
|
|
43
|
+
"typebox": "*"
|
|
44
|
+
},
|
|
45
|
+
"devDependencies": {
|
|
46
|
+
"@earendil-works/pi-coding-agent": "1.5.2",
|
|
47
|
+
"@vitest/coverage-v8": "5.1.0",
|
|
48
|
+
"typebox": "1.3.27",
|
|
49
|
+
"vitest": "5.1.0"
|
|
50
|
+
}
|
|
51
|
+
}
|
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Keep imports at top of file and avoid inline imports
|
|
3
|
+
alwaysApply: true
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# No inline imports
|
|
7
|
+
|
|
8
|
+
Always place imports at the top of the module. Avoid inline imports in function bodies, type annotations, or interface fields unless there is a strict circular-dependency reason and it is documented.
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Use exhaustive switch handling for TypeScript unions and enums
|
|
3
|
+
alwaysApply: true
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
typescript-exhaustive-switch: In switch statements over discriminated unions or enums, use a `never` check in the default case so newly added variants cause compile-time failures until handled.
|
|
@@ -0,0 +1,81 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: architect
|
|
3
|
+
description: "Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /skill:architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape."
|
|
4
|
+
disable-model-invocation: true
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# Architect
|
|
8
|
+
|
|
9
|
+
Bundled skills live at `../<name>/SKILL.md` from this file.
|
|
10
|
+
|
|
11
|
+
Sketch types, function signatures, class shapes, and module boundaries with `not implemented` bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch.
|
|
12
|
+
|
|
13
|
+
## Start
|
|
14
|
+
|
|
15
|
+
Write `TODO.md` with one `- [ ]` entry per phase before starting.
|
|
16
|
+
|
|
17
|
+
1. Ground
|
|
18
|
+
2. Sketch
|
|
19
|
+
3. Agree
|
|
20
|
+
4. Implement
|
|
21
|
+
5. Scrap
|
|
22
|
+
|
|
23
|
+
## Phase A: Ground the problem
|
|
24
|
+
|
|
25
|
+
Build a real mental model of every system the new code touches. Trace the relevant subsystems. Naming a file isn't grounding. Write an architectural explanation of each. If the design redefines ownership or layering, also run the **why** skill on the existing shape so the rationale becomes a constraint, not a guess.
|
|
26
|
+
|
|
27
|
+
Skip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.
|
|
28
|
+
|
|
29
|
+
## Phase B: Sketch
|
|
30
|
+
|
|
31
|
+
Run the **arena** skill with the design-sketch task and the Phase A grounding artifacts. Pass `references/runner-prompt.md` as each runner's prompt.
|
|
32
|
+
|
|
33
|
+
Take the runners from the `architect runners` line in the `pstack-models` system-prompt section, in place of the `arena runners` line. If that line is missing, the runners run on the session model, so omit `model`, and the panel is one model. Say so. Alias and rejected entries follow the runner rules in the **arena** skill's Phase A.
|
|
34
|
+
|
|
35
|
+
Design it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.
|
|
36
|
+
|
|
37
|
+
Screen every candidate against [`references/design-red-flags.md`](references/design-red-flags.md) before synthesis. Assume the next contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Prefer the design where a change that looks right from one file is right for the whole repo.
|
|
38
|
+
|
|
39
|
+
Compare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.
|
|
40
|
+
|
|
41
|
+
Arena returns one synthesized design package. Its synthesis decision fills the rationale's "Synthesis decision" section.
|
|
42
|
+
|
|
43
|
+
## Phase C: Agree (opt-in)
|
|
44
|
+
|
|
45
|
+
Default: proceed directly to implementation with the synthesized design. No human checkpoint.
|
|
46
|
+
|
|
47
|
+
Opt in to a checkpoint when the invoker explicitly asks: "/skill:architect with checkpoint," "stop and show me before implementing," or similar. Then surface the synthesized design and pause for sign-off.
|
|
48
|
+
|
|
49
|
+
The synthesis can ship as its own commit either way, as the "scaffold first" mode of the **foundational-thinking** principle skill. Planned and scoped breakage during fill-in is fine, per the **outcome-oriented-execution** principle skill. For adversarial pressure on the design before implementing, run the **interrogate** skill on the synthesized sketch.
|
|
50
|
+
|
|
51
|
+
If the human pushes back on the shape (in a checkpoint or after the fact), treat that as Phase A evidence. Re-ground and re-run Phase B before writing more code.
|
|
52
|
+
|
|
53
|
+
## Phase D: Implement against the sketch
|
|
54
|
+
|
|
55
|
+
Replace `not implemented` bodies with code, pseudocode with logic. The synthesized sketch is the contract. Deviations from it are signal to surface, not friction to absorb silently. If a function needs a parameter the sketch didn't anticipate, ask whether the sketch was wrong, the requirement was missed, or the implementation is overreaching.
|
|
56
|
+
|
|
57
|
+
## Phase E: Scrap when the architecture is wrong
|
|
58
|
+
|
|
59
|
+
If implementation keeps producing friction the sketch can't absorb, throw the sketch out. Don't bolt fixes onto a wrong design, per the **redesign-from-first-principles** and **fix-root-causes** principle skills.
|
|
60
|
+
|
|
61
|
+
The signal is a *pattern*, not single instances. Tells:
|
|
62
|
+
|
|
63
|
+
- The same shape of workaround appearing repeatedly across unrelated code.
|
|
64
|
+
- Multiple unrelated edge cases that all need special-case branches.
|
|
65
|
+
- Types that need escape hatches (`any`, casts, optional fields always set in practice) to compile.
|
|
66
|
+
- The "we need a lock" reflex when the sketch said the state wasn't shared.
|
|
67
|
+
- Callers having to know the abstraction's internal rules to use it.
|
|
68
|
+
- Two or more independent Phase D deviations of the same shape across the implementation.
|
|
69
|
+
|
|
70
|
+
Use judgment. A few edge cases don't condemn an architecture. Some problems are legitimately complex. Complexity in the data is not complexity in the design.
|
|
71
|
+
|
|
72
|
+
When you scrap:
|
|
73
|
+
|
|
74
|
+
1. Trace what's been built.
|
|
75
|
+
2. Redesign as if the new constraints had been day-one assumptions, per redesign-from-first-principles.
|
|
76
|
+
3. Subtract before adding, per the **subtract-before-you-add** principle skill. The new sketch should be smaller than the old one before it grows.
|
|
77
|
+
4. Return to Phase B and re-run arena.
|
|
78
|
+
|
|
79
|
+
## Outputs
|
|
80
|
+
|
|
81
|
+
The caller's usage is written first and the type sketch derived from it. One file with new types and signatures for small changes. Module map plus type definitions for larger work. The rationale ships alongside, shaped per `references/rationale-template.md`, including the usage sketch and the synthesis decision.
|
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
# Design red flags
|
|
2
|
+
|
|
3
|
+
Screen every candidate before synthesis. A red flag is a reason to revise or reject the shape.
|
|
4
|
+
|
|
5
|
+
## Shallow module
|
|
6
|
+
|
|
7
|
+
A shallow module exposes a large interface while hiding little complexity. Judge depth by the capability and policy hidden behind the public surface relative to the size of that surface. Prefer a simple interface backed by substantial behavior.
|
|
8
|
+
|
|
9
|
+
Do not confuse a deep module with a deep call chain. A deep call chain scatters understanding across layers. A deep module concentrates capability behind one interface.
|
|
10
|
+
|
|
11
|
+
Look for these signs:
|
|
12
|
+
|
|
13
|
+
- Callers coordinate several methods to complete one operation.
|
|
14
|
+
- Public options expose internal stages or implementation choices.
|
|
15
|
+
- Learning the interface does not save the caller from learning the implementation.
|
|
16
|
+
|
|
17
|
+
## Information leakage
|
|
18
|
+
|
|
19
|
+
Information leakage makes multiple modules depend on the same internal decision. A representation, policy, or protocol detail appears in more than one place, so changing it requires coordinated edits.
|
|
20
|
+
|
|
21
|
+
Public re-exports of transport or wire types are leakage. Parse external data into domain types behind the interface. Keep storage schemas, framework objects, and protocol details private.
|
|
22
|
+
|
|
23
|
+
## Temporal decomposition
|
|
24
|
+
|
|
25
|
+
Temporal decomposition organizes modules by execution order instead of the knowledge they own. Separate load, validate, transform, and save stages often repeat one representation and its invariants across several boundaries.
|
|
26
|
+
|
|
27
|
+
Group code around domain knowledge and ownership. Methods that run at different times can still belong to one module when they protect the same decisions.
|
|
28
|
+
|
|
29
|
+
## Pass-through method
|
|
30
|
+
|
|
31
|
+
A pass-through method forwards the same arguments to another method with the same shape. It adds a layer without hiding complexity.
|
|
32
|
+
|
|
33
|
+
Remove it or move responsibility to the module that can complete the operation. Keep a forwarding boundary only when it adds policy, adaptation, or a distinct abstraction.
|
|
34
|
+
|
|
35
|
+
## Split ownership
|
|
36
|
+
|
|
37
|
+
More than one module writes the same state or keeps its own copy of it. An agent that edits one writer can't see the others, so their rules diverge.
|
|
38
|
+
|
|
39
|
+
Give each piece of state one owner. Other modules read it or ask the owner to change it.
|
|
40
|
+
|
|
41
|
+
## Two ways to do one task
|
|
42
|
+
|
|
43
|
+
The design supports more than one way to do the same task. An agent copies whichever way it finds first, so every way keeps gaining callers.
|
|
44
|
+
|
|
45
|
+
Keep one way. Move callers off the others and delete them in the same change.
|
|
46
|
+
|
|
47
|
+
## Importable internals
|
|
48
|
+
|
|
49
|
+
A caller can import a module's internals. An agent takes the shortest path that compiles, so it imports them directly and they become part of the interface.
|
|
50
|
+
|
|
51
|
+
Make internals unreachable from outside the module, so an import from outside fails the build.
|
|
52
|
+
|
|
53
|
+
## Hand-synced list
|
|
54
|
+
|
|
55
|
+
Two or more places list the same items, and adding an item means editing every list. An agent that sees one list updates only that one.
|
|
56
|
+
|
|
57
|
+
Keep one list and derive the others from it. If a list can't be derived, make the build fail when the lists disagree.
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
# Rationale template
|
|
2
|
+
|
|
3
|
+
The prose that ships alongside the type sketch. One page. Sentence-case headings, no boilerplate. Replace the italic notes with actual content.
|
|
4
|
+
|
|
5
|
+
## Problem
|
|
6
|
+
|
|
7
|
+
*One paragraph. What we're trying to do, and what about the existing system or constraints makes the shape non-obvious. If [Phase A](../SKILL.md#phase-a-ground-the-problem) surfaced constraints the design must honor (existing types to interop with, callers we can't break, invariants that crossed our boundary), name them here so the reader sees the same constraints you saw.*
|
|
8
|
+
|
|
9
|
+
## Usage (caller's view)
|
|
10
|
+
|
|
11
|
+
*Write this first, before the type sketch. Show the README or quickstart the consumer reads, plus two or three realistic call sites in their own code. What they import, what they call, what comes back. The type sketch in [Shape](#shape) is derived from this. The two must agree. When they diverge, reconcile the sketch to the usage, not the reverse. The caller's experience is the spec. The types serve it.*
|
|
12
|
+
|
|
13
|
+
## Shape
|
|
14
|
+
|
|
15
|
+
*The recommended architecture. Data structures first. Then how data flows through the signatures. Name the load-bearing decisions. State which invariants are encoded in types, where validation lives, and what the system deliberately does not do. Judge interface depth explicitly. State what complexity the public surface hides, what remains exposed to callers, and why the interface is no larger than needed. Cite the principle behind each decision (e.g., `per boundary-discipline`). Don't restate it.*
|
|
16
|
+
|
|
17
|
+
## Synthesis decision
|
|
18
|
+
|
|
19
|
+
*Filled in by [arena](../../arena/SKILL.md). Records which candidate became the base and why, what was adapted from each of the others, and what was rejected and why.*
|
|
20
|
+
|
|
21
|
+
## Tradeoffs accepted
|
|
22
|
+
|
|
23
|
+
*One bullet per tradeoff the chosen shape makes. Form: "we accept X in exchange for Y." Name anything a future reader might mistake for an oversight, including things that look like premature optimization or premature simplification.*
|
|
24
|
+
|
|
25
|
+
## Alternatives considered
|
|
26
|
+
|
|
27
|
+
*Required. Name at least one concrete alternative shape, with one line on why it lost. Judge each alternative on interface depth, not implementation simplicity alone. Name the complexity it exposes to callers and the complexity it hides. Two or three alternatives belong here when the design space had real contenders. One is fine when the constraints forced the answer, with the conclusion phrased as "this was the only viable shape because..." Avoid listing flavors of the same shape. This section covers design alternatives the chosen shape considered and rejected, not other runner candidates.*
|
|
28
|
+
|
|
29
|
+
## Open questions and risks
|
|
30
|
+
|
|
31
|
+
*Things you noticed during the sketch that the human needs to weigh in on, and risks worth flagging before implementation starts. Phrase as questions, not assertions, so the human's answer is the resolution rather than a comment.*
|
|
32
|
+
|
|
33
|
+
## Next implementation step
|
|
34
|
+
|
|
35
|
+
*The first thing to build against the sketch. One sentence. What you'd start writing immediately after synthesis (or after Phase D sign-off, if a checkpoint was opted into).*
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
# Architect runner prompt
|
|
2
|
+
|
|
3
|
+
The orchestrator passes this file through to every parallel candidate runner during Phase B and fills in the variable inputs around it: the task, the Phase A grounding artifacts, the isolated working directory, and the path to write outputs. The working directory is a git worktree when available, otherwise a per-runner subdirectory under the sketch dir. What matters is independence between candidates.
|
|
4
|
+
|
|
5
|
+
You are producing one candidate design in architect's parallel exploration. Read the **architect** skill in full first. That's the workflow you're inside. Output a candidate design package: type sketch, function signatures, module map, and prose rationale shaped per [`rationale-template.md`](rationale-template.md).
|
|
6
|
+
|
|
7
|
+
Apply the following discipline. The orchestrator compares candidates on these axes to pick a base.
|
|
8
|
+
|
|
9
|
+
- Caller's usage first. Write the README-style usage and two or three real call sites before the types, then derive the type sketch from them. The usage is the spec. The two must agree, so reconcile the sketch to the usage, not the reverse.
|
|
10
|
+
- Data structures first. Get the core types right and the code becomes obvious. Trace each dominant access pattern through the proposed structure. If the answer is "we'll add a map / index / cache later," the structure is wrong.
|
|
11
|
+
- Interface depth. Compare the capability hidden behind the public surface relative to the size of that surface. Prefer a simple interface that pulls complexity into the callee, even when the implementation becomes less simple. Do not put transport or wire types on the public API. Parse into domain types behind the interface.
|
|
12
|
+
- Shared state: if two actors might both write, ask "what happens?" If the answer isn't "nothing," default to per-actor state with a merge at the read boundary, per the **separate-before-serializing-shared-state** principle skill.
|
|
13
|
+
- Make boundaries visible. `not implemented` errors for bodies, `// TODO` pseudocode for tricky logic, doc comments stating intent and invariants. A reader should trace data from input to output by reading types and signatures alone.
|
|
14
|
+
- Encode invariants in types: hard-to-misuse types > runtime checks > prose comments, per the **encode-lessons-in-structure** principle skill.
|
|
15
|
+
- Validate at boundaries, trust types inside, per the **boundary-discipline** principle skill. Business logic as pure functions. The shell stays thin.
|
|
16
|
+
- Single source of truth per invariant. Derive instead of sync.
|
|
17
|
+
- Idempotent state transitions where applicable, per the **make-operations-idempotent** principle skill. Ask what happens if the operation runs twice or crashes halfway.
|
|
18
|
+
- Short call chains. If tracing the flow needs more than three files, flatten the hierarchy, per the **laziness-protocol** and **minimize-reader-load** principle skills.
|
|
19
|
+
|
|
20
|
+
You are one of the parallel runners, each on a different model. Produce the best design your model can make. Don't hedge against the others. Differences between candidates are the signal used to pick a base and graft. Converging on a safe-looking middle defeats the exploration.
|