heimdall-agent 1.0.0 → 1.2.0
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/README.md +57 -26
- package/README.pt-BR.md +443 -0
- package/agents/cloud-engineer.md +77 -0
- package/agents/code-sentinel.md +71 -34
- package/agents/database-architect.md +31 -25
- package/agents/frontend-designer.md +30 -28
- package/agents/mobile-designer.md +25 -24
- package/agents/modernizer.md +68 -0
- package/agents/orchestrator.md +107 -93
- package/agents/reviewer.md +102 -71
- package/agents/security-auditor.md +27 -27
- package/agents/tester.md +97 -90
- package/commands/grill-me.md +20 -4
- package/commands/orchestrate.md +16 -0
- package/commands/orchestrator.md +16 -0
- package/commands/plan.md +17 -1
- package/config/agents.json +31 -3
- package/config/mcp.json +72 -0
- package/config/models.json +26 -16
- package/config/profiles.json +2 -4
- package/config/skills.json +762 -573
- package/docs/SKILLS.md +393 -275
- package/docs/designs/old/2026-10-31 plan-lifecycle-backlog-and-clean-code-skill.md +87 -0
- package/docs/designs/old/2026-11-02 skill-upstream-audit-and-update.md +105 -0
- package/docs/designs/old/2026-11-05 communication-doctrine-bluf-ste.md +94 -0
- package/docs/designs/old/2026-11-06-cloud-engineer-and-resilience-synthesis.md +67 -0
- package/docs/designs/old/2026-11-06-herdr-native-agent-orchestration.md +45 -0
- package/docs/runs/skill-audit/2026-11-12-compare-report.json +1028 -0
- package/docs/runs/skill-audit/2026-11-12-upstream-audit.json +275 -0
- package/docs/runs/skill-audit/add_progressive_disclosure.cjs +30 -0
- package/docs/runs/skill-audit/check_heimdall_skills.ps1 +9 -0
- package/docs/runs/skill-audit/compare_classics.ps1 +26 -0
- package/docs/runs/skill-audit/compare_taste.ps1 +12 -0
- package/docs/runs/skill-audit/customization-report.json +380 -0
- package/docs/runs/skill-audit/diff_pending_skills.cjs +94 -0
- package/docs/runs/skill-audit/fetch_and_apply_skill.cjs +58 -0
- package/docs/runs/skill-audit/fetch_and_apply_taste_v2.cjs +65 -0
- package/docs/runs/skill-audit/inspect_pending_skills.cjs +71 -0
- package/docs/runs/skill-audit/inventory.json +308 -0
- package/docs/runs/skill-audit/list_local_taste.ps1 +1 -0
- package/docs/runs/skill-audit/phase5-update-plan.json +595 -0
- package/docs/runs/skill-audit/phase5-update-plan.md +138 -0
- package/docs/runs/skill-audit/probe.ps1 +16 -0
- package/docs/runs/skill-audit/probe_classics_branches.ps1 +3 -0
- package/docs/runs/skill-audit/probe_commits.ps1 +15 -0
- package/docs/runs/skill-audit/probe_repos.ps1 +17 -0
- package/docs/runs/skill-audit/probe_sentry_sec.ps1 +3 -0
- package/docs/runs/skill-audit/probe_sentry_sweep.ps1 +5 -0
- package/docs/runs/skill-audit/probe_snyk.ps1 +3 -0
- package/docs/runs/skill-audit/probe_snyk_recipes.ps1 +5 -0
- package/docs/runs/skill-audit/probe_taste_branches.ps1 +8 -0
- package/docs/runs/skill-audit/probe_taste_v19.ps1 +3 -0
- package/docs/runs/skill-audit/probe_user_repos.ps1 +19 -0
- package/docs/runs/skill-audit/prune_taste_skills.cjs +22 -0
- package/docs/runs/skill-audit/run_phase1_2.cjs +142 -0
- package/docs/runs/skill-audit/run_phase6_verification.cjs +107 -0
- package/docs/runs/skill-audit/show_16_details.ps1 +25 -0
- package/docs/runs/skill-audit/show_20_skills.ps1 +28 -0
- package/docs/runs/skill-audit/show_classics_diff.cjs +37 -0
- package/docs/runs/skill-audit/sync_agent_markdowns.cjs +30 -0
- package/docs/runs/skill-audit/taste-skill-upstream.md +542 -0
- package/docs/runs/skill-audit/update-manifest.md +88 -0
- package/docs/runs/skill-audit/update_config_skills.cjs +52 -0
- package/docs/runs/skill-audit/update_registry_phase7.cjs +83 -0
- package/docs/runs/skill-audit/upstream-status.json +563 -0
- package/docs/runs/skill-audit/verification-results.json +252 -0
- package/doctrine/AGENTS.md +42 -77
- package/hooks/git/pre-commit +11 -0
- package/hooks/heimdall-hook.cjs +81 -2
- package/hooks/herdr-agent-state.ps1 +55 -0
- package/hooks/hooks.json +0 -11
- package/lib/catalog-sync.cjs +167 -0
- package/lib/hermes-context.cjs +57 -0
- package/lib/model-context.cjs +123 -0
- package/lib/path-discovery.cjs +94 -0
- package/package.json +7 -3
- package/playbooks/01-interactive-grilling-gate.md +23 -6
- package/playbooks/02-fast-code-deep-verification.md +3 -2
- package/playbooks/03-adversarial-code-review.md +15 -7
- package/playbooks/05-canonical-plan-template.md +35 -19
- package/playbooks/06-model-registry-matrix.md +24 -13
- package/playbooks/07-legacy-code-modernization.md +74 -0
- package/playbooks/08-backlog-and-change-request-flow.md +122 -0
- package/setup.mjs +592 -172
- package/skills/antislop/SKILL.md +76 -56
- package/skills/antislop/VERSION +1 -0
- package/skills/antislop-copywriting/SKILL.md +407 -372
- package/skills/antislop-human/LICENSE-web-quality-skills +21 -0
- package/skills/antislop-human/SKILL.md +204 -147
- package/skills/antislop-human/contrast-check.py +168 -165
- package/skills/antislop-human/contrast-mcp.py +6 -3
- package/skills/antislop-human/references/A11Y-PATTERNS.md +249 -0
- package/skills/antislop-human/references/WCAG.md +127 -0
- package/skills/antislop-ui/LICENSE-web-quality-skills +21 -0
- package/skills/antislop-ui/SKILL.md +344 -304
- package/skills/antislop-ui/references/CORE-WEB-VITALS.md +181 -0
- package/skills/antislop-ui/references/WEB-BASELINE.md +28 -0
- package/skills/brainstorming/SKILL.md +296 -265
- package/skills/brainstorming/builder-check-prompt.md +23 -0
- package/skills/brainstorming/scripts/frame-template.html +213 -213
- package/skills/brainstorming/scripts/server.cjs +723 -723
- package/skills/brandkit/SKILL.md +798 -798
- package/skills/brutalist-skill/SKILL.md +93 -92
- package/skills/caveman/README.md +68 -0
- package/skills/caveman/SKILL.md +73 -38
- package/skills/claude-collaborator/SKILL.md +24 -44
- package/skills/clean-code/SKILL.md +152 -0
- package/skills/cloudflare-security-audit/AI-AND-LLM.md +83 -83
- package/skills/cloudflare-security-audit/ATTACK-CLASSES.md +130 -130
- package/skills/cloudflare-security-audit/CLIENT-SIDE.md +83 -83
- package/skills/cloudflare-security-audit/CLOUD-AND-DEPLOYMENT.md +86 -86
- package/skills/cloudflare-security-audit/DATA-ISOLATION-AND-LIFECYCLE.md +84 -84
- package/skills/cloudflare-security-audit/DESKTOP-MOBILE-AND-LOCAL-IPC.md +89 -89
- package/skills/cloudflare-security-audit/HUNTING.md +251 -251
- package/skills/cloudflare-security-audit/MEMORY-SAFETY-AND-BINARY.md +101 -101
- package/skills/cloudflare-security-audit/PROTOCOLS-RPC-AND-MESSAGING.md +81 -81
- package/skills/cloudflare-security-audit/RECONNAISSANCE.md +156 -156
- package/skills/cloudflare-security-audit/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md +78 -78
- package/skills/cloudflare-security-audit/SKILL.md +192 -192
- package/skills/cloudflare-security-audit/SUPPLY-CHAIN-AND-RELEASE.md +73 -73
- package/skills/cloudflare-security-audit/VALIDATION-AND-REPORTING.md +186 -186
- package/skills/cloudflare-security-audit/WEB-PROTOCOL-AND-AUTH.md +105 -105
- package/skills/cloudflare-security-audit/report-schema.json +461 -461
- package/skills/cloudflare-security-audit/validate-coverage-ledger.cjs +872 -872
- package/skills/cloudflare-security-audit/validate-coverage-ledger.test.cjs +740 -740
- package/skills/cloudflare-security-audit/validate-findings.cjs +773 -773
- package/skills/cloudflare-security-audit/validate-findings.test.cjs +652 -652
- package/skills/codebase-design/DEEPENING.md +37 -0
- package/skills/codebase-design/DESIGN-IT-TWICE.md +44 -0
- package/skills/codebase-design/SKILL.md +114 -0
- package/skills/codex-collaborator/SKILL.md +24 -45
- package/skills/communication-doctrine/SKILL.md +89 -0
- package/skills/diagnosing-superpowers/SKILL.md +1 -1
- package/skills/diagnosing-superpowers/references/github-issues.md +3 -3
- package/skills/diagnosing-superpowers/templates/issue.md +23 -4
- package/skills/domain-modeling/ADR-FORMAT.md +47 -0
- package/skills/domain-modeling/GLOSSARY-FORMAT.md +60 -0
- package/skills/domain-modeling/SKILL.md +74 -0
- package/skills/executing-plans/SKILL.md +6 -56
- package/skills/executing-plans/scripts/task-done +52 -52
- package/skills/executing-plans/scripts/task-start +28 -28
- package/skills/gemini-collaborator/SKILL.md +24 -56
- package/skills/grill-me/SKILL.md +65 -0
- package/skills/handoff/SKILL.md +64 -0
- package/skills/herdr/SKILL.md +243 -0
- package/skills/image-to-code-skill/SKILL.md +1228 -1228
- package/skills/imagegen-frontend-mobile/SKILL.md +1465 -1465
- package/skills/imagegen-frontend-web/SKILL.md +987 -987
- package/skills/improve-codebase-architecture/HTML-REPORT.md +123 -0
- package/skills/improve-codebase-architecture/SKILL.md +71 -0
- package/skills/karpathy-guidelines/SKILL.md +67 -67
- package/skills/mcp-engineering/SKILL.md +74 -0
- package/skills/minimalist-skill/SKILL.md +87 -85
- package/skills/output-skill/SKILL.md +49 -49
- package/skills/owasp-security/reference/config-and-supply-chain.md +346 -344
- package/skills/owasp-security/reference/languages.md +378 -372
- package/skills/owasp-security/reference/owasp-report.md +1144 -1140
- package/skills/owasp-security/reference/review-checklist.md +134 -132
- package/skills/ponytail/SKILL.md +36 -52
- package/skills/postgres-best-practices/SKILL.md +30 -52
- package/skills/postgres-best-practices/references/backup-restore.md +372 -0
- package/skills/postgres-best-practices/references/bulk-loading.md +315 -0
- package/skills/postgres-best-practices/references/connection-pooling.md +310 -0
- package/skills/postgres-best-practices/references/hot-standby.md +221 -0
- package/skills/postgres-best-practices/references/indexing.md +318 -0
- package/skills/postgres-best-practices/references/logical-replication.md +610 -0
- package/skills/postgres-best-practices/references/major-version-upgrades.md +334 -0
- package/skills/postgres-best-practices/references/performance-diagnostics.md +553 -0
- package/skills/postgres-best-practices/references/query-optimization.md +294 -0
- package/skills/postgres-best-practices/references/query-patterns.md +566 -0
- package/skills/postgres-best-practices/references/schema-design.md +362 -0
- package/skills/postgres-best-practices/references/security-roles.md +489 -0
- package/skills/postgres-best-practices/references/transaction-isolation.md +344 -0
- package/skills/progressive-disclosure/SKILL.md +68 -0
- package/skills/pstack-discipline/SKILL.md +40 -0
- package/skills/receiving-code-review/SKILL.md +2 -23
- package/skills/requesting-code-review/SKILL.md +7 -36
- package/skills/soft-skill/SKILL.md +99 -98
- package/skills/stitch-skill/DESIGN.md +121 -121
- package/skills/stitch-skill/SKILL.md +185 -184
- package/skills/strix-security/SKILL.md +54 -53
- package/skills/subagent-driven-development/SKILL.md +35 -264
- package/skills/subagent-driven-development/references/batching.md +11 -0
- package/skills/subagent-driven-development/references/cannot-verify.md +10 -0
- package/skills/subagent-driven-development/references/final-review.md +47 -0
- package/skills/subagent-driven-development/references/fix-loop.md +77 -0
- package/skills/subagent-driven-development/references/handling-reports.md +15 -0
- package/skills/subagent-driven-development/references/preflight.md +26 -0
- package/skills/subagent-driven-development/references/resuming.md +12 -0
- package/skills/subagent-driven-development/scripts/review-package +53 -53
- package/skills/subagent-driven-development/scripts/sdd-workspace +87 -82
- package/skills/subagent-driven-development/scripts/task-brief +43 -43
- package/skills/systematic-debugging/SKILL.md +283 -306
- package/skills/taste-skill/SKILL.md +542 -1206
- package/skills/taste-skill/references/app-screens.md +1199 -0
- package/skills/taste-skill/references/colour.md +141 -0
- package/skills/taste-skill/references/copy.md +177 -0
- package/skills/taste-skill/references/critique.md +182 -0
- package/skills/taste-skill/references/imagery.md +791 -0
- package/skills/taste-skill/references/layout.md +292 -0
- package/skills/taste-skill/references/motion.md +980 -0
- package/skills/taste-skill/references/research.md +356 -0
- package/skills/taste-skill/references/scenes.md +174 -0
- package/skills/taste-skill/references/tells.md +115 -0
- package/skills/taste-skill/references/type.md +170 -0
- package/skills/test-driven-development/SKILL.md +330 -337
- package/skills/thermo/SKILL.md +67 -0
- package/skills/threat-modeling/SKILL.md +55 -0
- package/skills/to-spec/SKILL.md +75 -0
- package/skills/to-tickets/SKILL.md +105 -0
- package/skills/trailofbits-audit-context/SKILL.md +72 -72
- package/skills/trailofbits-insecure-defaults/commands/audit.md +35 -0
- package/skills/trailofbits-insecure-defaults/references/debug-features.json +13 -13
- package/skills/trailofbits-insecure-defaults/references/debug-features.md +75 -75
- package/skills/trailofbits-insecure-defaults/references/default-credentials.json +12 -12
- package/skills/trailofbits-insecure-defaults/references/default-credentials.md +76 -76
- package/skills/trailofbits-insecure-defaults/references/fail-open-security.json +11 -11
- package/skills/trailofbits-insecure-defaults/references/fail-open-security.md +70 -70
- package/skills/trailofbits-insecure-defaults/references/fallback-secrets.json +11 -11
- package/skills/trailofbits-insecure-defaults/references/fallback-secrets.md +70 -70
- package/skills/trailofbits-insecure-defaults/references/permissive-access.json +13 -13
- package/skills/trailofbits-insecure-defaults/references/permissive-access.md +62 -62
- package/skills/trailofbits-insecure-defaults/references/weak-crypto.json +13 -13
- package/skills/trailofbits-insecure-defaults/references/weak-crypto.md +71 -71
- package/skills/trailofbits-triage-brocards/SKILL.md +208 -208
- package/skills/verification-before-completion/SKILL.md +0 -14
- package/skills/wayfinder/SKILL.md +128 -0
- package/skills/writing-plans/SKILL.md +11 -15
- package/skills/writing-skills/SKILL.md +21 -303
- package/skills/writing-skills/references/CLAUDE_MD_TESTING.md +189 -0
- package/skills/writing-skills/references/anthropic-best-practices.md +1150 -0
- package/skills/writing-skills/references/bulletproofing.md +80 -0
- package/skills/writing-skills/references/discovery.md +201 -0
- package/skills/writing-skills/references/flowcharts.md +37 -0
- package/skills/writing-skills/references/graphviz-conventions.dot +172 -0
- package/skills/writing-skills/references/persuasion-principles.md +187 -0
- package/skills/writing-skills/references/testing-skills-with-subagents.md +384 -0
- package/tools/{claude-bridge.ps1 → archive/claude-bridge.ps1} +10 -7
- package/tools/{codex-bridge.ps1 → archive/codex-bridge.ps1} +1 -1
- package/tools/{gemini-bridge.ps1 → archive/gemini-bridge.ps1} +12 -19
- package/skills/gpt-tasteskill/SKILL.md +0 -74
- package/skills/taste-skill-v1/SKILL.md +0 -226
- /package/tools/{claude-bridge.cmd → archive/claude-bridge.cmd} +0 -0
- /package/tools/{claude-bridge.sh → archive/claude-bridge.sh} +0 -0
- /package/tools/{codex-bridge.cmd → archive/codex-bridge.cmd} +0 -0
- /package/tools/{codex-bridge.sh → archive/codex-bridge.sh} +0 -0
- /package/tools/{codexcli-bridge.cmd → archive/codexcli-bridge.cmd} +0 -0
- /package/tools/{codexcli-bridge.ps1 → archive/codexcli-bridge.ps1} +0 -0
- /package/tools/{gemini-bridge.cmd → archive/gemini-bridge.cmd} +0 -0
- /package/tools/{gemini-bridge.sh → archive/gemini-bridge.sh} +0 -0
|
@@ -70,23 +70,13 @@ digraph process {
|
|
|
70
70
|
"Implementer implements, tests, commits, self-reviews" [shape=box];
|
|
71
71
|
"Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" [shape=box];
|
|
72
72
|
"Spec ✅ and quality approved?" [shape=diamond];
|
|
73
|
-
"
|
|
74
|
-
"Rule on the conflict, ledger the ruling" [shape=box];
|
|
75
|
-
"Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [shape=box];
|
|
76
|
-
"Dispatch scoped re-review (./re-review-prompt.md)" [shape=box];
|
|
77
|
-
"All findings addressed?" [shape=diamond];
|
|
78
|
-
"R = 5?" [shape=diamond];
|
|
79
|
-
"Adjudicate each open finding" [shape=box];
|
|
80
|
-
"Any load-bearing finding?" [shape=diamond];
|
|
81
|
-
"Rule and continue; stop only if every path forward is a guess" [shape=box];
|
|
82
|
-
"Park findings in ledger with rulings" [shape=box];
|
|
73
|
+
"Fix loop: read references/fix-loop.md before every round" [shape=box];
|
|
83
74
|
"Append completion to ledger, mark todo complete" [shape=box];
|
|
84
75
|
}
|
|
85
76
|
|
|
86
77
|
"Setup: worktree, ledger check, read plan, pre-flight review" [shape=box];
|
|
87
78
|
"More tasks remain?" [shape=diamond];
|
|
88
|
-
"
|
|
89
|
-
"Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" [shape=box];
|
|
79
|
+
"Final review and finish: read references/final-review.md" [shape=box];
|
|
90
80
|
"Final review clean: delete this plan's workspace" [shape=box];
|
|
91
81
|
"Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
|
|
92
82
|
|
|
@@ -98,25 +88,12 @@ digraph process {
|
|
|
98
88
|
"Implementer implements, tests, commits, self-reviews" -> "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)";
|
|
99
89
|
"Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" -> "Spec ✅ and quality approved?";
|
|
100
90
|
"Spec ✅ and quality approved?" -> "Append completion to ledger, mark todo complete" [label="yes"];
|
|
101
|
-
"Spec ✅ and quality approved?" -> "
|
|
102
|
-
"
|
|
103
|
-
"Rule on the conflict, ledger the ruling" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model";
|
|
104
|
-
"Finding conflicts with plan text?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no"];
|
|
105
|
-
"Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" -> "Dispatch scoped re-review (./re-review-prompt.md)";
|
|
106
|
-
"Dispatch scoped re-review (./re-review-prompt.md)" -> "All findings addressed?";
|
|
107
|
-
"All findings addressed?" -> "Append completion to ledger, mark todo complete" [label="yes"];
|
|
108
|
-
"All findings addressed?" -> "R = 5?" [label="no"];
|
|
109
|
-
"R = 5?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no - next round"];
|
|
110
|
-
"R = 5?" -> "Adjudicate each open finding" [label="yes - breaker trips"];
|
|
111
|
-
"Adjudicate each open finding" -> "Any load-bearing finding?";
|
|
112
|
-
"Any load-bearing finding?" -> "Rule and continue; stop only if every path forward is a guess" [label="yes"];
|
|
113
|
-
"Any load-bearing finding?" -> "Park findings in ledger with rulings" [label="no"];
|
|
114
|
-
"Park findings in ledger with rulings" -> "Append completion to ledger, mark todo complete";
|
|
91
|
+
"Spec ✅ and quality approved?" -> "Fix loop: read references/fix-loop.md before every round" [label="no"];
|
|
92
|
+
"Fix loop: read references/fix-loop.md before every round" -> "Append completion to ledger, mark todo complete" [label="addressed, or parked at the cap"];
|
|
115
93
|
"Append completion to ledger, mark todo complete" -> "More tasks remain?";
|
|
116
94
|
"More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
|
|
117
|
-
"More tasks remain?" -> "
|
|
118
|
-
"
|
|
119
|
-
"Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" -> "Final review clean: delete this plan's workspace";
|
|
95
|
+
"More tasks remain?" -> "Final review and finish: read references/final-review.md" [label="no"];
|
|
96
|
+
"Final review and finish: read references/final-review.md" -> "Final review clean: delete this plan's workspace";
|
|
120
97
|
"Final review clean: delete this plan's workspace" -> "Use superpowers:finishing-a-development-branch";
|
|
121
98
|
}
|
|
122
99
|
```
|
|
@@ -134,17 +111,14 @@ sequences — the single most expensive failure observed. Track progress in
|
|
|
134
111
|
a ledger file, not only in todos.
|
|
135
112
|
|
|
136
113
|
- Each plan owns a workspace: at skill start, run this skill's
|
|
137
|
-
`bash scripts/sdd-workspace PLAN_FILE`
|
|
114
|
+
`bash scripts/sdd-workspace PLAN_FILE` by its absolute path, from the
|
|
115
|
+
working tree you're executing in — it prints the plan's git-ignored
|
|
138
116
|
directory (under `<repo-root>/.superpowers/sdd/`), home to
|
|
139
117
|
every artifact for THIS plan: ledger, briefs, reports, review packages.
|
|
140
118
|
Another plan's directory is never yours to read or write.
|
|
141
|
-
- Check for this plan's ledger at `<workspace>/progress.md`. If
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
whose last line is a fix round is mid-loop: resume the loop at the next
|
|
145
|
-
round. A ledger whose first line names a different plan file — or a stray
|
|
146
|
-
ledger at the old flat path `.superpowers/sdd/progress.md` — is another
|
|
147
|
-
plan's progress: leave it in place and start your own, fresh.
|
|
119
|
+
- Check for this plan's ledger at `<workspace>/progress.md`. If one exists,
|
|
120
|
+
read [references/resuming.md](references/resuming.md) before anything
|
|
121
|
+
else: it says whose ledger it is and where to resume.
|
|
148
122
|
- Create the ledger with its identity as the first line:
|
|
149
123
|
`# SDD ledger — plan: <plan file path>`.
|
|
150
124
|
- The ledger is your recovery map: the commits it names exist in git even
|
|
@@ -159,27 +133,9 @@ authority the plan argues from, and conflicts inside the plan resolve
|
|
|
159
133
|
against it. A plan with no reachable spec gets a ledger note saying so —
|
|
160
134
|
rulings made without one are provisional.
|
|
161
135
|
|
|
162
|
-
Before dispatching Task 1,
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
- tasks that contradict each other or the plan's Global Constraints
|
|
166
|
-
- anything the plan explicitly mandates that the review rubric treats as a
|
|
167
|
-
defect (a test that asserts nothing, verbatim duplication of a logic block)
|
|
168
|
-
|
|
169
|
-
The scan's output is a table, not a verdict. One row for every pair of tasks
|
|
170
|
-
that share a file or an interface: the two tasks, what one produces against
|
|
171
|
-
what the other consumes, and what you found. One row for every task: whether
|
|
172
|
-
its own text agrees with itself — the tests it specifies against the code it
|
|
173
|
-
specifies, the files it creates against the files it later touches. "The scan
|
|
174
|
-
is clean" without those rows is not a scan you ran.
|
|
175
|
-
|
|
176
|
-
Write the table to the ledger. Rule on everything you find before execution
|
|
177
|
-
begins — each finding against the plan text that mandates it — and record
|
|
178
|
-
each ruling in the ledger. If the scan is clean, proceed without comment.
|
|
179
|
-
Rule on each conflict it surfaces — the spec is the binding authority, the
|
|
180
|
-
plan is its argument — record the ruling beside its row, and dispatch
|
|
181
|
-
Task 1. The review loop remains the net for conflicts that only emerge from
|
|
182
|
-
implementation.
|
|
136
|
+
Before dispatching Task 1, read [references/preflight.md](references/preflight.md)
|
|
137
|
+
and run the conflict scan it describes. Its table and rulings go in the
|
|
138
|
+
ledger.
|
|
183
139
|
|
|
184
140
|
## Model Selection
|
|
185
141
|
|
|
@@ -220,13 +176,9 @@ that implementer. Single-file mechanical fixes also take the cheapest tier.
|
|
|
220
176
|
|
|
221
177
|
## The Task Loop
|
|
222
178
|
|
|
223
|
-
**
|
|
224
|
-
|
|
225
|
-
|
|
226
|
-
one subagent per task. Compose ONE dispatch brief listing every file and
|
|
227
|
-
its change, send the whole batch to a single subagent, and review its diff
|
|
228
|
-
as one unit. Reserve one-dispatch-per-task for work that needs its own
|
|
229
|
-
judgment, its own tests, or its own review surface.
|
|
179
|
+
**Small same-shape work:** when the plan lists several small edits of the
|
|
180
|
+
same kind across files, read [references/batching.md](references/batching.md)
|
|
181
|
+
before dispatching them.
|
|
230
182
|
|
|
231
183
|
Everything you paste into a dispatch prompt — and everything a subagent
|
|
232
184
|
prints back — stays resident in your context for the rest of the session
|
|
@@ -249,7 +201,8 @@ Record BASE (`git rev-parse HEAD`) before dispatching — the review package
|
|
|
249
201
|
and fix-round diffs need it.
|
|
250
202
|
|
|
251
203
|
- **Task brief:** before dispatching an implementer, run this skill's
|
|
252
|
-
`bash scripts/task-brief PLAN_FILE N`
|
|
204
|
+
`bash scripts/task-brief PLAN_FILE N` by its absolute path, from the
|
|
205
|
+
working tree you're executing in — it extracts the task's full text to a
|
|
253
206
|
uniquely named file and prints the path. Compose the dispatch so the
|
|
254
207
|
brief stays the single source of
|
|
255
208
|
requirements. Your dispatch should contain: (1) one line on where this
|
|
@@ -287,19 +240,11 @@ Template: [implementer-prompt.md](implementer-prompt.md)
|
|
|
287
240
|
|
|
288
241
|
Implementer subagents report one of four statuses. Handle each appropriately:
|
|
289
242
|
|
|
290
|
-
**DONE:** Generate the review package (`bash scripts/review-package PLAN_FILE BASE HEAD
|
|
291
|
-
|
|
292
|
-
**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
|
|
243
|
+
**DONE:** Generate the review package (`bash scripts/review-package PLAN_FILE BASE HEAD` by its absolute path, from the working tree you're executing in — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never `HEAD~1`, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.
|
|
293
244
|
|
|
294
|
-
**
|
|
295
|
-
|
|
296
|
-
|
|
297
|
-
1. If it's a context problem, provide more context and re-dispatch with the same model
|
|
298
|
-
2. If the task requires more reasoning, re-dispatch with a more capable model
|
|
299
|
-
3. If the task is too large, break it into smaller pieces
|
|
300
|
-
4. If the plan itself is wrong, rule on the correction, ledger it, and re-dispatch with the ruling carried in the dispatch
|
|
301
|
-
|
|
302
|
-
**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
|
|
245
|
+
**Any other status** (DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED): read
|
|
246
|
+
[references/handling-reports.md](references/handling-reports.md) and follow
|
|
247
|
+
it, every time you get one.
|
|
303
248
|
|
|
304
249
|
If the implementer asks questions — before starting or mid-task — answer
|
|
305
250
|
clearly and completely, provide additional context if needed, and don't
|
|
@@ -314,7 +259,8 @@ required. Implementer self-review never replaces the task review; both are
|
|
|
314
259
|
needed.
|
|
315
260
|
|
|
316
261
|
- Hand the reviewer its diff as a file: run this skill's
|
|
317
|
-
`bash scripts/review-package PLAN_FILE BASE HEAD`
|
|
262
|
+
`bash scripts/review-package PLAN_FILE BASE HEAD` by its absolute path, from
|
|
263
|
+
the working tree you're executing in, and pass the reviewer the file path
|
|
318
264
|
it prints (or, without bash: `git log --oneline`, `git diff --stat`,
|
|
319
265
|
and `git diff -U10` for the range, redirected to one uniquely named
|
|
320
266
|
file). The output never enters your own context, and the reviewer sees
|
|
@@ -342,12 +288,9 @@ needed.
|
|
|
342
288
|
loop. If the prompt you are writing contains "do not flag," "don't treat X
|
|
343
289
|
as a defect," "at most Minor," or "the plan chose" — stop: you are
|
|
344
290
|
pre-judging, usually to spare yourself a review loop.
|
|
345
|
-
|
|
346
|
-
|
|
347
|
-
|
|
348
|
-
complete: you hold the plan and cross-task context the reviewer
|
|
349
|
-
lacks. If you confirm an item is a real gap, treat it as a failed spec
|
|
350
|
-
review — it enters the fix loop with the other findings.
|
|
291
|
+
If the reviewer reports "⚠️ Cannot verify from diff" items, read
|
|
292
|
+
[references/cannot-verify.md](references/cannot-verify.md) before you mark
|
|
293
|
+
the task complete.
|
|
351
294
|
|
|
352
295
|
Template: [task-reviewer-prompt.md](task-reviewer-prompt.md)
|
|
353
296
|
|
|
@@ -356,77 +299,10 @@ Template: [task-reviewer-prompt.md](task-reviewer-prompt.md)
|
|
|
356
299
|
The loop triggers when the review reports spec ❌, any Critical or Important
|
|
357
300
|
finding, or a ⚠️ item you confirmed as a real gap.
|
|
358
301
|
|
|
359
|
-
|
|
360
|
-
|
|
361
|
-
|
|
362
|
-
|
|
363
|
-
whole-branch review at that list so it can triage which must be fixed
|
|
364
|
-
before merge. A roll-up nobody reads is a silent discard. Minor findings
|
|
365
|
-
never enter the loop.
|
|
366
|
-
- A finding labeled plan-mandated — or any finding that conflicts with
|
|
367
|
-
what the plan's text requires — is yours to rule on: weigh the finding
|
|
368
|
-
against the plan text, decide with the spec as the binding authority, and
|
|
369
|
-
ledger the ruling before you act on it. Do not dismiss the finding because
|
|
370
|
-
the plan mandates it, and do not dispatch a fix that contradicts the plan
|
|
371
|
-
without a recorded ruling.
|
|
372
|
-
Everything else enters the loop. A fix round is one fix dispatch plus one
|
|
373
|
-
scoped re-review. Five rounds maximum per task:
|
|
374
|
-
|
|
375
|
-
**Rounds 1-3 — resume the original implementer.** Send it the open findings
|
|
376
|
-
verbatim. Its context is intact: it knows the task, the code, and its own
|
|
377
|
-
choices. If your harness cannot send another message to a live subagent,
|
|
378
|
-
dispatch a fresh implementer carrying the brief path, the report-file path,
|
|
379
|
-
and the findings — the report file is the persistent memory either way.
|
|
380
|
-
|
|
381
|
-
**Rounds 4-5 — dispatch a fresh implementer on a more capable model** (per
|
|
382
|
-
Model Selection), with the brief path, the report-file path, the open
|
|
383
|
-
findings, and this framing: "A prior implementer attempted this task
|
|
384
|
-
[N] times; you own it now. Read the report file for what was tried." A loop
|
|
385
|
-
that survives three resumes usually means the implementer cannot see its
|
|
386
|
-
own problem — fresh eyes and a capability bump in one move.
|
|
387
|
-
|
|
388
|
-
**Every round, either way:** the implementer fixes, re-runs the tests
|
|
389
|
-
covering the amended code, appends its fix report to the same report file,
|
|
390
|
-
and returns the short contract. Before re-dispatching the reviewer, confirm
|
|
391
|
-
the fix report contains the covering tests, the command run, and the
|
|
392
|
-
output; dispatch the re-review once all three are present. Name the
|
|
393
|
-
covering test files in the fix message — a one-line fix does not need the
|
|
394
|
-
whole suite.
|
|
395
|
-
|
|
396
|
-
**The re-review is scoped.** Run `bash scripts/review-package PLAN_FILE FIX_BASE HEAD`
|
|
397
|
-
where FIX_BASE is the head the previous review saw, and dispatch
|
|
398
|
-
[re-review-prompt.md](re-review-prompt.md) with the findings list, the
|
|
399
|
-
brief, the report file, and the printed diff path. The re-reviewer verdicts
|
|
400
|
-
each finding ADDRESSED or NOT ADDRESSED and flags new breakage in the fix
|
|
401
|
-
diff only. New Critical/Important breakage in the fix diff joins the open
|
|
402
|
-
findings list. Out-of-scope observations go to the ledger as deferred
|
|
403
|
-
minors — they never extend the loop.
|
|
404
|
-
|
|
405
|
-
**After each round,** append to the ledger:
|
|
406
|
-
`Task <N>: fix round <R>/5 (<X> addressed, <Y> open — <finding one-liners>; commits <a7>..<b7>)`
|
|
407
|
-
|
|
408
|
-
Never fix findings yourself in the controller session — your context stays
|
|
409
|
-
clean for coordination, and controller fixes skip review.
|
|
410
|
-
|
|
411
|
-
**The breaker.** When round 5's re-review still leaves findings open, stop
|
|
412
|
-
dispatching. Adjudicate each open finding yourself — you hold the plan and
|
|
413
|
-
the cross-task context the reviewer lacks:
|
|
414
|
-
|
|
415
|
-
- **The reviewer is wrong, or the point is contestable:** park it —
|
|
416
|
-
`Task <N>: parked — <finding> — Ruling: <why the code stands>`. The final
|
|
417
|
-
review sees both sides.
|
|
418
|
-
- **Real, but nothing downstream builds on it:** park it the same way, with
|
|
419
|
-
a ruling that says it's real and deferred.
|
|
420
|
-
- **Real and load-bearing** — a later task builds on it, or it reveals a
|
|
421
|
-
plan defect: rule on the smallest change that unblocks the dependent work,
|
|
422
|
-
ledger it as `Task <N>: Ruling: <finding> — <what you decided and why>`,
|
|
423
|
-
and carry it into the next task's dispatch. Parking a structural failure
|
|
424
|
-
silently lets every dependent task build on it. Stop only when the defect
|
|
425
|
-
leaves every path forward a guess.
|
|
426
|
-
|
|
427
|
-
Adjudicate only at the cap. Adjudicating earlier to end a loop is
|
|
428
|
-
pre-judging with a different name. Every adjudication is a ledger entry —
|
|
429
|
-
a silent discard is forbidden.
|
|
302
|
+
When it triggers, read [references/fix-loop.md](references/fix-loop.md) and
|
|
303
|
+
follow it. Read it again before every round, even if you read it earlier in
|
|
304
|
+
this session: it holds the round cap, the breaker, and the ledger line each
|
|
305
|
+
round writes, and your memory of it does not survive compaction.
|
|
430
306
|
|
|
431
307
|
### 5. Complete the task
|
|
432
308
|
|
|
@@ -444,47 +320,9 @@ parked-with-ruling at the cap.
|
|
|
444
320
|
|
|
445
321
|
## Final Review
|
|
446
322
|
|
|
447
|
-
|
|
448
|
-
|
|
449
|
-
branch
|
|
450
|
-
printed path in the final review dispatch, so the final reviewer reads
|
|
451
|
-
one file instead of re-deriving the branch diff with git commands. Dispatch
|
|
452
|
-
on the most capable available model (see Model Selection), using
|
|
453
|
-
superpowers:requesting-code-review's
|
|
454
|
-
[code-reviewer.md](../requesting-code-review/code-reviewer.md). Point it at
|
|
455
|
-
the ledger's deferred-minor and parked lines so it can triage which must be
|
|
456
|
-
fixed before merge.
|
|
457
|
-
|
|
458
|
-
If the final whole-branch review returns findings, dispatch ONE fix subagent
|
|
459
|
-
with the complete findings list — not one fixer per finding.
|
|
460
|
-
Per-finding fixers each rebuild context and re-run suites; a real
|
|
461
|
-
session's final-review fix wave cost more than all its tasks combined.
|
|
462
|
-
Then run exactly one scoped re-review of the fix wave
|
|
463
|
-
(`bash scripts/review-package PLAN_FILE FIX_BASE HEAD` over the fix range,
|
|
464
|
-
[re-review-prompt.md](re-review-prompt.md)).
|
|
465
|
-
Adjudicate any residual findings as in the task loop's breaker: park with
|
|
466
|
-
rulings, or rule on the load-bearing ones and ledger what you decided. Only
|
|
467
|
-
the four classes above stop you here. There is no second fix wave —
|
|
468
|
-
residual load-bearing findings surface to your human partner when
|
|
469
|
-
finishing-a-development-branch presents the options.
|
|
470
|
-
|
|
471
|
-
## Finish
|
|
472
|
-
|
|
473
|
-
Before you delete anything, collect every ledger line containing `Ruling:` —
|
|
474
|
-
preflight rulings, parked findings, breaker adjudications, all of them — into
|
|
475
|
-
your final message under "Rulings I made", in the order you made them, each
|
|
476
|
-
with what it costs if wrong. The list is exhaustive: if the ledger holds a
|
|
477
|
-
ruling, the list holds it. That list is the only place the decisions you
|
|
478
|
-
took on your human partner's behalf reach them — they read it and rework
|
|
479
|
-
whatever you got wrong. A ruling that dies with the workspace was a decision
|
|
480
|
-
made in secret.
|
|
481
|
-
|
|
482
|
-
When the final whole-branch review is clean and its fixes are merged,
|
|
483
|
-
delete this plan's workspace (`rm -rf <workspace>`) — the git history is
|
|
484
|
-
the record now. Sibling directories belong to other plans; leave them
|
|
485
|
-
alone.
|
|
486
|
-
|
|
487
|
-
Use superpowers:finishing-a-development-branch.
|
|
323
|
+
When every task is complete, read
|
|
324
|
+
[references/final-review.md](references/final-review.md) and follow it. It
|
|
325
|
+
covers the whole-branch review, its single fix wave, and how you finish.
|
|
488
326
|
|
|
489
327
|
## Common Rationalizations
|
|
490
328
|
|
|
@@ -499,70 +337,3 @@ Use superpowers:finishing-a-development-branch.
|
|
|
499
337
|
| "Reviews slow the loop down" | The loop without reviews is just unverified churn. Reviews are the loop's brakes and steering. |
|
|
500
338
|
| "Ledger bookkeeping is overhead" | The ledger is what survives compaction. Controllers without one have re-dispatched entire completed task sequences. |
|
|
501
339
|
| "The implementer spawned its own reviewer — free extra assurance" | It's a duplicate seat reviewing the same diff; the task review is the gate. A worker-spawned reviewer is a defect to flag, not rigor. |
|
|
502
|
-
|
|
503
|
-
## Example Workflow
|
|
504
|
-
|
|
505
|
-
```
|
|
506
|
-
You: I'm using Subagent-Driven Development to execute this plan.
|
|
507
|
-
|
|
508
|
-
[Setup: worktree verified]
|
|
509
|
-
[Read plan file once: docs/superpowers/plans/feature-plan.md]
|
|
510
|
-
[Resolve workspace: bash scripts/sdd-workspace docs/superpowers/plans/feature-plan.md — no ledger inside, fresh start]
|
|
511
|
-
[Create todos for all tasks]
|
|
512
|
-
|
|
513
|
-
Task 1: Hook installation script
|
|
514
|
-
|
|
515
|
-
[Run task-brief for Task 1; dispatch implementer with brief + report paths + context]
|
|
516
|
-
|
|
517
|
-
Implementer: "Before I begin - should the hook be installed at user or system level?"
|
|
518
|
-
|
|
519
|
-
You: "User level (~/.config/superpowers/hooks/)"
|
|
520
|
-
|
|
521
|
-
Implementer: [Later]
|
|
522
|
-
- Implemented install-hook command
|
|
523
|
-
- Added tests, 5/5 passing
|
|
524
|
-
- Self-review: Found I missed --force flag, added it
|
|
525
|
-
- Committed
|
|
526
|
-
|
|
527
|
-
[Run review-package PLAN_FILE BASE HEAD; dispatch task reviewer with the printed path]
|
|
528
|
-
Task reviewer: Spec ✅ - all requirements met, nothing extra.
|
|
529
|
-
Strengths: Good test coverage, clean. Issues: None. Task quality: Approved.
|
|
530
|
-
|
|
531
|
-
[Ledger: Task 1: complete (commits a1b2c3d..d4e5f6a, review clean)]
|
|
532
|
-
|
|
533
|
-
Task 2: Recovery modes
|
|
534
|
-
|
|
535
|
-
[Run task-brief for Task 2; dispatch implementer with brief + report paths + context]
|
|
536
|
-
|
|
537
|
-
Implementer: [No questions]
|
|
538
|
-
- Added verify/repair modes
|
|
539
|
-
- 8/8 tests passing
|
|
540
|
-
- Committed
|
|
541
|
-
|
|
542
|
-
[Run review-package PLAN_FILE BASE HEAD; dispatch task reviewer with the printed path]
|
|
543
|
-
Task reviewer: Spec ❌:
|
|
544
|
-
- Missing: Progress reporting (spec says "report every 100 items")
|
|
545
|
-
Issues (Important): Magic number (100)
|
|
546
|
-
|
|
547
|
-
[Fix round 1: resume the implementer with both findings]
|
|
548
|
-
Implementer: Added progress reporting, extracted PROGRESS_INTERVAL constant.
|
|
549
|
-
Re-ran test/recovery.test.js — 10/10 passing. Fix report appended.
|
|
550
|
-
|
|
551
|
-
[Run review-package PLAN_FILE FIX_BASE HEAD; dispatch scoped re-review]
|
|
552
|
-
Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
|
|
553
|
-
Magic number — ADDRESSED (src/recovery.js:7). New breakage: none.
|
|
554
|
-
Verdict: all findings addressed.
|
|
555
|
-
|
|
556
|
-
[Ledger: Task 2: fix round 1/5 (2 addressed, 0 open; commits d4e5f6a..b7c8d9e)]
|
|
557
|
-
[Ledger: Task 2: complete (commits d4e5f6a..b7c8d9e, review clean)]
|
|
558
|
-
|
|
559
|
-
...
|
|
560
|
-
|
|
561
|
-
[After all tasks]
|
|
562
|
-
[Run review-package PLAN_FILE MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
|
|
563
|
-
Final reviewer: All requirements met. Deferred minors triaged: none block merge.
|
|
564
|
-
|
|
565
|
-
[Delete this plan's workspace — the record now lives in git]
|
|
566
|
-
|
|
567
|
-
Done! Using superpowers:finishing-a-development-branch.
|
|
568
|
-
```
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
# Batching Small Same-Shape Work
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development.
|
|
4
|
+
|
|
5
|
+
**Batch small same-shape work.** When the plan lists several tasks that are
|
|
6
|
+
each a small, independent edit of the same kind — the same one-line fix,
|
|
7
|
+
constant change, or field addition repeated across files — do not dispatch
|
|
8
|
+
one subagent per task. Compose ONE dispatch brief listing every file and
|
|
9
|
+
its change, send the whole batch to a single subagent, and review its diff
|
|
10
|
+
as one unit. Reserve one-dispatch-per-task for work that needs its own
|
|
11
|
+
judgment, its own tests, or its own review surface.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
# "Cannot Verify From Diff" Items
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development.
|
|
4
|
+
|
|
5
|
+
The task reviewer may report "⚠️ Cannot verify from diff" items — requirements
|
|
6
|
+
that live in unchanged code or span tasks. These do not block the rest of the
|
|
7
|
+
review, but you must resolve each one yourself before marking the task
|
|
8
|
+
complete: you hold the plan and cross-task context the reviewer
|
|
9
|
+
lacks. If you confirm an item is a real gap, treat it as a failed spec
|
|
10
|
+
review — it enters the fix loop with the other findings.
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
# Final Review and Finish
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development. Every task in the plan is
|
|
4
|
+
complete.
|
|
5
|
+
|
|
6
|
+
The final whole-branch review gets a package too: run
|
|
7
|
+
`bash scripts/review-package PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the commit the
|
|
8
|
+
branch started from, e.g. `git merge-base main HEAD`) and include the
|
|
9
|
+
printed path in the final review dispatch, so the final reviewer reads
|
|
10
|
+
one file instead of re-deriving the branch diff with git commands. Dispatch
|
|
11
|
+
on the most capable available model (see SKILL.md's Model Selection), using
|
|
12
|
+
superpowers:requesting-code-review's
|
|
13
|
+
[code-reviewer.md](../../requesting-code-review/code-reviewer.md). Point it at
|
|
14
|
+
the ledger's deferred-minor and parked lines so it can triage which must be
|
|
15
|
+
fixed before merge.
|
|
16
|
+
|
|
17
|
+
If the final whole-branch review returns findings, dispatch ONE fix subagent
|
|
18
|
+
with the complete findings list — not one fixer per finding.
|
|
19
|
+
Per-finding fixers each rebuild context and re-run suites; a real
|
|
20
|
+
session's final-review fix wave cost more than all its tasks combined.
|
|
21
|
+
Then run exactly one scoped re-review of the fix wave
|
|
22
|
+
(`bash scripts/review-package PLAN_FILE FIX_BASE HEAD` over the fix range,
|
|
23
|
+
[re-review-prompt.md](../re-review-prompt.md)).
|
|
24
|
+
Adjudicate any residual findings as in the fix loop's breaker
|
|
25
|
+
(references/fix-loop.md): park with rulings, or rule on the load-bearing
|
|
26
|
+
ones and ledger what you decided. Only the four things that stop a running
|
|
27
|
+
plan (top of SKILL.md) stop you here. There is no second fix wave —
|
|
28
|
+
residual load-bearing findings surface to your human partner when
|
|
29
|
+
finishing-a-development-branch presents the options.
|
|
30
|
+
|
|
31
|
+
### Finish
|
|
32
|
+
|
|
33
|
+
Before you delete anything, collect every ledger line containing `Ruling:` —
|
|
34
|
+
preflight rulings, parked findings, breaker adjudications, all of them — into
|
|
35
|
+
your final message under "Rulings I made", in the order you made them, each
|
|
36
|
+
with what it costs if wrong. The list is exhaustive: if the ledger holds a
|
|
37
|
+
ruling, the list holds it. That list is the only place the decisions you
|
|
38
|
+
took on your human partner's behalf reach them — they read it and rework
|
|
39
|
+
whatever you got wrong. A ruling that dies with the workspace was a decision
|
|
40
|
+
made in secret.
|
|
41
|
+
|
|
42
|
+
When the final whole-branch review is clean and its fixes are merged,
|
|
43
|
+
delete this plan's workspace (`rm -rf <workspace>`) — the git history is
|
|
44
|
+
the record now. Sibling directories belong to other plans; leave them
|
|
45
|
+
alone.
|
|
46
|
+
|
|
47
|
+
Use superpowers:finishing-a-development-branch.
|
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
# The Fix Loop
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development. The task review reported
|
|
4
|
+
spec ❌, a Critical or Important finding, or a ⚠️ item you confirmed as a real
|
|
5
|
+
gap.
|
|
6
|
+
|
|
7
|
+
Before the loop starts, two routes leave it immediately:
|
|
8
|
+
|
|
9
|
+
- Record Minor findings in the progress ledger as you go
|
|
10
|
+
(`Task <N>: minor (deferred): <one-liner>`), and point the final
|
|
11
|
+
whole-branch review at that list so it can triage which must be fixed
|
|
12
|
+
before merge. A roll-up nobody reads is a silent discard. Minor findings
|
|
13
|
+
never enter the loop.
|
|
14
|
+
- A finding labeled plan-mandated — or any finding that conflicts with
|
|
15
|
+
what the plan's text requires — is yours to rule on: weigh the finding
|
|
16
|
+
against the plan text, decide with the spec as the binding authority, and
|
|
17
|
+
ledger the ruling before you act on it. Do not dismiss the finding because
|
|
18
|
+
the plan mandates it, and do not dispatch a fix that contradicts the plan
|
|
19
|
+
without a recorded ruling.
|
|
20
|
+
Everything else enters the loop. A fix round is one fix dispatch plus one
|
|
21
|
+
scoped re-review. Five rounds maximum per task:
|
|
22
|
+
|
|
23
|
+
**Rounds 1-3 — resume the original implementer.** Send it the open findings
|
|
24
|
+
verbatim. Its context is intact: it knows the task, the code, and its own
|
|
25
|
+
choices. If your harness cannot send another message to a live subagent,
|
|
26
|
+
dispatch a fresh implementer carrying the brief path, the report-file path,
|
|
27
|
+
and the findings — the report file is the persistent memory either way.
|
|
28
|
+
|
|
29
|
+
**Rounds 4-5 — dispatch a fresh implementer on a more capable model** (per
|
|
30
|
+
SKILL.md's Model Selection), with the brief path, the report-file path, the open
|
|
31
|
+
findings, and this framing: "A prior implementer attempted this task
|
|
32
|
+
[N] times; you own it now. Read the report file for what was tried." A loop
|
|
33
|
+
that survives three resumes usually means the implementer cannot see its
|
|
34
|
+
own problem — fresh eyes and a capability bump in one move.
|
|
35
|
+
|
|
36
|
+
**Every round, either way:** the implementer fixes, re-runs the tests
|
|
37
|
+
covering the amended code, appends its fix report to the same report file,
|
|
38
|
+
and returns the short contract. Before re-dispatching the reviewer, confirm
|
|
39
|
+
the fix report contains the covering tests, the command run, and the
|
|
40
|
+
output; dispatch the re-review once all three are present. Name the
|
|
41
|
+
covering test files in the fix message — a one-line fix does not need the
|
|
42
|
+
whole suite.
|
|
43
|
+
|
|
44
|
+
**The re-review is scoped.** Run `bash scripts/review-package PLAN_FILE FIX_BASE HEAD`
|
|
45
|
+
where FIX_BASE is the head the previous review saw, and dispatch
|
|
46
|
+
[re-review-prompt.md](../re-review-prompt.md) with the findings list, the
|
|
47
|
+
brief, the report file, and the printed diff path. The re-reviewer verdicts
|
|
48
|
+
each finding ADDRESSED or NOT ADDRESSED and flags new breakage in the fix
|
|
49
|
+
diff only. New Critical/Important breakage in the fix diff joins the open
|
|
50
|
+
findings list. Out-of-scope observations go to the ledger as deferred
|
|
51
|
+
minors — they never extend the loop.
|
|
52
|
+
|
|
53
|
+
**After each round,** append to the ledger:
|
|
54
|
+
`Task <N>: fix round <R>/5 (<X> addressed, <Y> open — <finding one-liners>; commits <a7>..<b7>)`
|
|
55
|
+
|
|
56
|
+
Never fix findings yourself in the controller session — your context stays
|
|
57
|
+
clean for coordination, and controller fixes skip review.
|
|
58
|
+
|
|
59
|
+
**The breaker.** When round 5's re-review still leaves findings open, stop
|
|
60
|
+
dispatching. Adjudicate each open finding yourself — you hold the plan and
|
|
61
|
+
the cross-task context the reviewer lacks:
|
|
62
|
+
|
|
63
|
+
- **The reviewer is wrong, or the point is contestable:** park it —
|
|
64
|
+
`Task <N>: parked — <finding> — Ruling: <why the code stands>`. The final
|
|
65
|
+
review sees both sides.
|
|
66
|
+
- **Real, but nothing downstream builds on it:** park it the same way, with
|
|
67
|
+
a ruling that says it's real and deferred.
|
|
68
|
+
- **Real and load-bearing** — a later task builds on it, or it reveals a
|
|
69
|
+
plan defect: rule on the smallest change that unblocks the dependent work,
|
|
70
|
+
ledger it as `Task <N>: Ruling: <finding> — <what you decided and why>`,
|
|
71
|
+
and carry it into the next task's dispatch. Parking a structural failure
|
|
72
|
+
silently lets every dependent task build on it. Stop only when the defect
|
|
73
|
+
leaves every path forward a guess.
|
|
74
|
+
|
|
75
|
+
Adjudicate only at the cap. Adjudicating earlier to end a loop is
|
|
76
|
+
pre-judging with a different name. Every adjudication is a ledger entry —
|
|
77
|
+
a silent discard is forbidden.
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
# Handling a Report That Isn't DONE
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development.
|
|
4
|
+
|
|
5
|
+
**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
|
|
6
|
+
|
|
7
|
+
**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
|
|
8
|
+
|
|
9
|
+
**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
|
|
10
|
+
1. If it's a context problem, provide more context and re-dispatch with the same model
|
|
11
|
+
2. If the task requires more reasoning, re-dispatch with a more capable model
|
|
12
|
+
3. If the task is too large, break it into smaller pieces
|
|
13
|
+
4. If the plan itself is wrong, rule on the correction, ledger it, and re-dispatch with the ruling carried in the dispatch
|
|
14
|
+
|
|
15
|
+
**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
# The Pre-flight Scan
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development. Run it once, before
|
|
4
|
+
dispatching Task 1.
|
|
5
|
+
|
|
6
|
+
Before dispatching Task 1, scan the plan once for conflicts, writing down
|
|
7
|
+
what you checked as you check it:
|
|
8
|
+
|
|
9
|
+
- tasks that contradict each other or the plan's Global Constraints
|
|
10
|
+
- anything the plan explicitly mandates that the review rubric treats as a
|
|
11
|
+
defect (a test that asserts nothing, verbatim duplication of a logic block)
|
|
12
|
+
|
|
13
|
+
The scan's output is a table, not a verdict. One row for every pair of tasks
|
|
14
|
+
that share a file or an interface: the two tasks, what one produces against
|
|
15
|
+
what the other consumes, and what you found. One row for every task: whether
|
|
16
|
+
its own text agrees with itself — the tests it specifies against the code it
|
|
17
|
+
specifies, the files it creates against the files it later touches. "The scan
|
|
18
|
+
is clean" without those rows is not a scan you ran.
|
|
19
|
+
|
|
20
|
+
Write the table to the ledger. Rule on everything you find before execution
|
|
21
|
+
begins — each finding against the plan text that mandates it — and record
|
|
22
|
+
each ruling in the ledger. If the scan is clean, proceed without comment.
|
|
23
|
+
Rule on each conflict it surfaces — the spec is the binding authority, the
|
|
24
|
+
plan is its argument — record the ruling beside its row, and dispatch
|
|
25
|
+
Task 1. The review loop remains the net for conflicts that only emerge from
|
|
26
|
+
implementation.
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
# Resuming From an Existing Ledger
|
|
2
|
+
|
|
3
|
+
Part of superpowers:subagent-driven-development. This plan's workspace
|
|
4
|
+
already has a ledger at `<workspace>/progress.md`.
|
|
5
|
+
|
|
6
|
+
If the ledger's first line names your plan file, tasks with a `Task <N>:
|
|
7
|
+
complete` line are DONE — do not re-dispatch them; resume at the first
|
|
8
|
+
task without one. A task whose last line is a fix round is mid-loop:
|
|
9
|
+
resume the loop at the next round. A ledger whose first line names a
|
|
10
|
+
different plan file — or a stray ledger at the old flat path
|
|
11
|
+
`.superpowers/sdd/progress.md` — is another plan's progress: leave it in
|
|
12
|
+
place and start your own, fresh.
|