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.
Files changed (250) hide show
  1. package/README.md +57 -26
  2. package/README.pt-BR.md +443 -0
  3. package/agents/cloud-engineer.md +77 -0
  4. package/agents/code-sentinel.md +71 -34
  5. package/agents/database-architect.md +31 -25
  6. package/agents/frontend-designer.md +30 -28
  7. package/agents/mobile-designer.md +25 -24
  8. package/agents/modernizer.md +68 -0
  9. package/agents/orchestrator.md +107 -93
  10. package/agents/reviewer.md +102 -71
  11. package/agents/security-auditor.md +27 -27
  12. package/agents/tester.md +97 -90
  13. package/commands/grill-me.md +20 -4
  14. package/commands/orchestrate.md +16 -0
  15. package/commands/orchestrator.md +16 -0
  16. package/commands/plan.md +17 -1
  17. package/config/agents.json +31 -3
  18. package/config/mcp.json +72 -0
  19. package/config/models.json +26 -16
  20. package/config/profiles.json +2 -4
  21. package/config/skills.json +762 -573
  22. package/docs/SKILLS.md +393 -275
  23. package/docs/designs/old/2026-10-31 plan-lifecycle-backlog-and-clean-code-skill.md +87 -0
  24. package/docs/designs/old/2026-11-02 skill-upstream-audit-and-update.md +105 -0
  25. package/docs/designs/old/2026-11-05 communication-doctrine-bluf-ste.md +94 -0
  26. package/docs/designs/old/2026-11-06-cloud-engineer-and-resilience-synthesis.md +67 -0
  27. package/docs/designs/old/2026-11-06-herdr-native-agent-orchestration.md +45 -0
  28. package/docs/runs/skill-audit/2026-11-12-compare-report.json +1028 -0
  29. package/docs/runs/skill-audit/2026-11-12-upstream-audit.json +275 -0
  30. package/docs/runs/skill-audit/add_progressive_disclosure.cjs +30 -0
  31. package/docs/runs/skill-audit/check_heimdall_skills.ps1 +9 -0
  32. package/docs/runs/skill-audit/compare_classics.ps1 +26 -0
  33. package/docs/runs/skill-audit/compare_taste.ps1 +12 -0
  34. package/docs/runs/skill-audit/customization-report.json +380 -0
  35. package/docs/runs/skill-audit/diff_pending_skills.cjs +94 -0
  36. package/docs/runs/skill-audit/fetch_and_apply_skill.cjs +58 -0
  37. package/docs/runs/skill-audit/fetch_and_apply_taste_v2.cjs +65 -0
  38. package/docs/runs/skill-audit/inspect_pending_skills.cjs +71 -0
  39. package/docs/runs/skill-audit/inventory.json +308 -0
  40. package/docs/runs/skill-audit/list_local_taste.ps1 +1 -0
  41. package/docs/runs/skill-audit/phase5-update-plan.json +595 -0
  42. package/docs/runs/skill-audit/phase5-update-plan.md +138 -0
  43. package/docs/runs/skill-audit/probe.ps1 +16 -0
  44. package/docs/runs/skill-audit/probe_classics_branches.ps1 +3 -0
  45. package/docs/runs/skill-audit/probe_commits.ps1 +15 -0
  46. package/docs/runs/skill-audit/probe_repos.ps1 +17 -0
  47. package/docs/runs/skill-audit/probe_sentry_sec.ps1 +3 -0
  48. package/docs/runs/skill-audit/probe_sentry_sweep.ps1 +5 -0
  49. package/docs/runs/skill-audit/probe_snyk.ps1 +3 -0
  50. package/docs/runs/skill-audit/probe_snyk_recipes.ps1 +5 -0
  51. package/docs/runs/skill-audit/probe_taste_branches.ps1 +8 -0
  52. package/docs/runs/skill-audit/probe_taste_v19.ps1 +3 -0
  53. package/docs/runs/skill-audit/probe_user_repos.ps1 +19 -0
  54. package/docs/runs/skill-audit/prune_taste_skills.cjs +22 -0
  55. package/docs/runs/skill-audit/run_phase1_2.cjs +142 -0
  56. package/docs/runs/skill-audit/run_phase6_verification.cjs +107 -0
  57. package/docs/runs/skill-audit/show_16_details.ps1 +25 -0
  58. package/docs/runs/skill-audit/show_20_skills.ps1 +28 -0
  59. package/docs/runs/skill-audit/show_classics_diff.cjs +37 -0
  60. package/docs/runs/skill-audit/sync_agent_markdowns.cjs +30 -0
  61. package/docs/runs/skill-audit/taste-skill-upstream.md +542 -0
  62. package/docs/runs/skill-audit/update-manifest.md +88 -0
  63. package/docs/runs/skill-audit/update_config_skills.cjs +52 -0
  64. package/docs/runs/skill-audit/update_registry_phase7.cjs +83 -0
  65. package/docs/runs/skill-audit/upstream-status.json +563 -0
  66. package/docs/runs/skill-audit/verification-results.json +252 -0
  67. package/doctrine/AGENTS.md +42 -77
  68. package/hooks/git/pre-commit +11 -0
  69. package/hooks/heimdall-hook.cjs +81 -2
  70. package/hooks/herdr-agent-state.ps1 +55 -0
  71. package/hooks/hooks.json +0 -11
  72. package/lib/catalog-sync.cjs +167 -0
  73. package/lib/hermes-context.cjs +57 -0
  74. package/lib/model-context.cjs +123 -0
  75. package/lib/path-discovery.cjs +94 -0
  76. package/package.json +7 -3
  77. package/playbooks/01-interactive-grilling-gate.md +23 -6
  78. package/playbooks/02-fast-code-deep-verification.md +3 -2
  79. package/playbooks/03-adversarial-code-review.md +15 -7
  80. package/playbooks/05-canonical-plan-template.md +35 -19
  81. package/playbooks/06-model-registry-matrix.md +24 -13
  82. package/playbooks/07-legacy-code-modernization.md +74 -0
  83. package/playbooks/08-backlog-and-change-request-flow.md +122 -0
  84. package/setup.mjs +592 -172
  85. package/skills/antislop/SKILL.md +76 -56
  86. package/skills/antislop/VERSION +1 -0
  87. package/skills/antislop-copywriting/SKILL.md +407 -372
  88. package/skills/antislop-human/LICENSE-web-quality-skills +21 -0
  89. package/skills/antislop-human/SKILL.md +204 -147
  90. package/skills/antislop-human/contrast-check.py +168 -165
  91. package/skills/antislop-human/contrast-mcp.py +6 -3
  92. package/skills/antislop-human/references/A11Y-PATTERNS.md +249 -0
  93. package/skills/antislop-human/references/WCAG.md +127 -0
  94. package/skills/antislop-ui/LICENSE-web-quality-skills +21 -0
  95. package/skills/antislop-ui/SKILL.md +344 -304
  96. package/skills/antislop-ui/references/CORE-WEB-VITALS.md +181 -0
  97. package/skills/antislop-ui/references/WEB-BASELINE.md +28 -0
  98. package/skills/brainstorming/SKILL.md +296 -265
  99. package/skills/brainstorming/builder-check-prompt.md +23 -0
  100. package/skills/brainstorming/scripts/frame-template.html +213 -213
  101. package/skills/brainstorming/scripts/server.cjs +723 -723
  102. package/skills/brandkit/SKILL.md +798 -798
  103. package/skills/brutalist-skill/SKILL.md +93 -92
  104. package/skills/caveman/README.md +68 -0
  105. package/skills/caveman/SKILL.md +73 -38
  106. package/skills/claude-collaborator/SKILL.md +24 -44
  107. package/skills/clean-code/SKILL.md +152 -0
  108. package/skills/cloudflare-security-audit/AI-AND-LLM.md +83 -83
  109. package/skills/cloudflare-security-audit/ATTACK-CLASSES.md +130 -130
  110. package/skills/cloudflare-security-audit/CLIENT-SIDE.md +83 -83
  111. package/skills/cloudflare-security-audit/CLOUD-AND-DEPLOYMENT.md +86 -86
  112. package/skills/cloudflare-security-audit/DATA-ISOLATION-AND-LIFECYCLE.md +84 -84
  113. package/skills/cloudflare-security-audit/DESKTOP-MOBILE-AND-LOCAL-IPC.md +89 -89
  114. package/skills/cloudflare-security-audit/HUNTING.md +251 -251
  115. package/skills/cloudflare-security-audit/MEMORY-SAFETY-AND-BINARY.md +101 -101
  116. package/skills/cloudflare-security-audit/PROTOCOLS-RPC-AND-MESSAGING.md +81 -81
  117. package/skills/cloudflare-security-audit/RECONNAISSANCE.md +156 -156
  118. package/skills/cloudflare-security-audit/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md +78 -78
  119. package/skills/cloudflare-security-audit/SKILL.md +192 -192
  120. package/skills/cloudflare-security-audit/SUPPLY-CHAIN-AND-RELEASE.md +73 -73
  121. package/skills/cloudflare-security-audit/VALIDATION-AND-REPORTING.md +186 -186
  122. package/skills/cloudflare-security-audit/WEB-PROTOCOL-AND-AUTH.md +105 -105
  123. package/skills/cloudflare-security-audit/report-schema.json +461 -461
  124. package/skills/cloudflare-security-audit/validate-coverage-ledger.cjs +872 -872
  125. package/skills/cloudflare-security-audit/validate-coverage-ledger.test.cjs +740 -740
  126. package/skills/cloudflare-security-audit/validate-findings.cjs +773 -773
  127. package/skills/cloudflare-security-audit/validate-findings.test.cjs +652 -652
  128. package/skills/codebase-design/DEEPENING.md +37 -0
  129. package/skills/codebase-design/DESIGN-IT-TWICE.md +44 -0
  130. package/skills/codebase-design/SKILL.md +114 -0
  131. package/skills/codex-collaborator/SKILL.md +24 -45
  132. package/skills/communication-doctrine/SKILL.md +89 -0
  133. package/skills/diagnosing-superpowers/SKILL.md +1 -1
  134. package/skills/diagnosing-superpowers/references/github-issues.md +3 -3
  135. package/skills/diagnosing-superpowers/templates/issue.md +23 -4
  136. package/skills/domain-modeling/ADR-FORMAT.md +47 -0
  137. package/skills/domain-modeling/GLOSSARY-FORMAT.md +60 -0
  138. package/skills/domain-modeling/SKILL.md +74 -0
  139. package/skills/executing-plans/SKILL.md +6 -56
  140. package/skills/executing-plans/scripts/task-done +52 -52
  141. package/skills/executing-plans/scripts/task-start +28 -28
  142. package/skills/gemini-collaborator/SKILL.md +24 -56
  143. package/skills/grill-me/SKILL.md +65 -0
  144. package/skills/handoff/SKILL.md +64 -0
  145. package/skills/herdr/SKILL.md +243 -0
  146. package/skills/image-to-code-skill/SKILL.md +1228 -1228
  147. package/skills/imagegen-frontend-mobile/SKILL.md +1465 -1465
  148. package/skills/imagegen-frontend-web/SKILL.md +987 -987
  149. package/skills/improve-codebase-architecture/HTML-REPORT.md +123 -0
  150. package/skills/improve-codebase-architecture/SKILL.md +71 -0
  151. package/skills/karpathy-guidelines/SKILL.md +67 -67
  152. package/skills/mcp-engineering/SKILL.md +74 -0
  153. package/skills/minimalist-skill/SKILL.md +87 -85
  154. package/skills/output-skill/SKILL.md +49 -49
  155. package/skills/owasp-security/reference/config-and-supply-chain.md +346 -344
  156. package/skills/owasp-security/reference/languages.md +378 -372
  157. package/skills/owasp-security/reference/owasp-report.md +1144 -1140
  158. package/skills/owasp-security/reference/review-checklist.md +134 -132
  159. package/skills/ponytail/SKILL.md +36 -52
  160. package/skills/postgres-best-practices/SKILL.md +30 -52
  161. package/skills/postgres-best-practices/references/backup-restore.md +372 -0
  162. package/skills/postgres-best-practices/references/bulk-loading.md +315 -0
  163. package/skills/postgres-best-practices/references/connection-pooling.md +310 -0
  164. package/skills/postgres-best-practices/references/hot-standby.md +221 -0
  165. package/skills/postgres-best-practices/references/indexing.md +318 -0
  166. package/skills/postgres-best-practices/references/logical-replication.md +610 -0
  167. package/skills/postgres-best-practices/references/major-version-upgrades.md +334 -0
  168. package/skills/postgres-best-practices/references/performance-diagnostics.md +553 -0
  169. package/skills/postgres-best-practices/references/query-optimization.md +294 -0
  170. package/skills/postgres-best-practices/references/query-patterns.md +566 -0
  171. package/skills/postgres-best-practices/references/schema-design.md +362 -0
  172. package/skills/postgres-best-practices/references/security-roles.md +489 -0
  173. package/skills/postgres-best-practices/references/transaction-isolation.md +344 -0
  174. package/skills/progressive-disclosure/SKILL.md +68 -0
  175. package/skills/pstack-discipline/SKILL.md +40 -0
  176. package/skills/receiving-code-review/SKILL.md +2 -23
  177. package/skills/requesting-code-review/SKILL.md +7 -36
  178. package/skills/soft-skill/SKILL.md +99 -98
  179. package/skills/stitch-skill/DESIGN.md +121 -121
  180. package/skills/stitch-skill/SKILL.md +185 -184
  181. package/skills/strix-security/SKILL.md +54 -53
  182. package/skills/subagent-driven-development/SKILL.md +35 -264
  183. package/skills/subagent-driven-development/references/batching.md +11 -0
  184. package/skills/subagent-driven-development/references/cannot-verify.md +10 -0
  185. package/skills/subagent-driven-development/references/final-review.md +47 -0
  186. package/skills/subagent-driven-development/references/fix-loop.md +77 -0
  187. package/skills/subagent-driven-development/references/handling-reports.md +15 -0
  188. package/skills/subagent-driven-development/references/preflight.md +26 -0
  189. package/skills/subagent-driven-development/references/resuming.md +12 -0
  190. package/skills/subagent-driven-development/scripts/review-package +53 -53
  191. package/skills/subagent-driven-development/scripts/sdd-workspace +87 -82
  192. package/skills/subagent-driven-development/scripts/task-brief +43 -43
  193. package/skills/systematic-debugging/SKILL.md +283 -306
  194. package/skills/taste-skill/SKILL.md +542 -1206
  195. package/skills/taste-skill/references/app-screens.md +1199 -0
  196. package/skills/taste-skill/references/colour.md +141 -0
  197. package/skills/taste-skill/references/copy.md +177 -0
  198. package/skills/taste-skill/references/critique.md +182 -0
  199. package/skills/taste-skill/references/imagery.md +791 -0
  200. package/skills/taste-skill/references/layout.md +292 -0
  201. package/skills/taste-skill/references/motion.md +980 -0
  202. package/skills/taste-skill/references/research.md +356 -0
  203. package/skills/taste-skill/references/scenes.md +174 -0
  204. package/skills/taste-skill/references/tells.md +115 -0
  205. package/skills/taste-skill/references/type.md +170 -0
  206. package/skills/test-driven-development/SKILL.md +330 -337
  207. package/skills/thermo/SKILL.md +67 -0
  208. package/skills/threat-modeling/SKILL.md +55 -0
  209. package/skills/to-spec/SKILL.md +75 -0
  210. package/skills/to-tickets/SKILL.md +105 -0
  211. package/skills/trailofbits-audit-context/SKILL.md +72 -72
  212. package/skills/trailofbits-insecure-defaults/commands/audit.md +35 -0
  213. package/skills/trailofbits-insecure-defaults/references/debug-features.json +13 -13
  214. package/skills/trailofbits-insecure-defaults/references/debug-features.md +75 -75
  215. package/skills/trailofbits-insecure-defaults/references/default-credentials.json +12 -12
  216. package/skills/trailofbits-insecure-defaults/references/default-credentials.md +76 -76
  217. package/skills/trailofbits-insecure-defaults/references/fail-open-security.json +11 -11
  218. package/skills/trailofbits-insecure-defaults/references/fail-open-security.md +70 -70
  219. package/skills/trailofbits-insecure-defaults/references/fallback-secrets.json +11 -11
  220. package/skills/trailofbits-insecure-defaults/references/fallback-secrets.md +70 -70
  221. package/skills/trailofbits-insecure-defaults/references/permissive-access.json +13 -13
  222. package/skills/trailofbits-insecure-defaults/references/permissive-access.md +62 -62
  223. package/skills/trailofbits-insecure-defaults/references/weak-crypto.json +13 -13
  224. package/skills/trailofbits-insecure-defaults/references/weak-crypto.md +71 -71
  225. package/skills/trailofbits-triage-brocards/SKILL.md +208 -208
  226. package/skills/verification-before-completion/SKILL.md +0 -14
  227. package/skills/wayfinder/SKILL.md +128 -0
  228. package/skills/writing-plans/SKILL.md +11 -15
  229. package/skills/writing-skills/SKILL.md +21 -303
  230. package/skills/writing-skills/references/CLAUDE_MD_TESTING.md +189 -0
  231. package/skills/writing-skills/references/anthropic-best-practices.md +1150 -0
  232. package/skills/writing-skills/references/bulletproofing.md +80 -0
  233. package/skills/writing-skills/references/discovery.md +201 -0
  234. package/skills/writing-skills/references/flowcharts.md +37 -0
  235. package/skills/writing-skills/references/graphviz-conventions.dot +172 -0
  236. package/skills/writing-skills/references/persuasion-principles.md +187 -0
  237. package/skills/writing-skills/references/testing-skills-with-subagents.md +384 -0
  238. package/tools/{claude-bridge.ps1 → archive/claude-bridge.ps1} +10 -7
  239. package/tools/{codex-bridge.ps1 → archive/codex-bridge.ps1} +1 -1
  240. package/tools/{gemini-bridge.ps1 → archive/gemini-bridge.ps1} +12 -19
  241. package/skills/gpt-tasteskill/SKILL.md +0 -74
  242. package/skills/taste-skill-v1/SKILL.md +0 -226
  243. /package/tools/{claude-bridge.cmd → archive/claude-bridge.cmd} +0 -0
  244. /package/tools/{claude-bridge.sh → archive/claude-bridge.sh} +0 -0
  245. /package/tools/{codex-bridge.cmd → archive/codex-bridge.cmd} +0 -0
  246. /package/tools/{codex-bridge.sh → archive/codex-bridge.sh} +0 -0
  247. /package/tools/{codexcli-bridge.cmd → archive/codexcli-bridge.cmd} +0 -0
  248. /package/tools/{codexcli-bridge.ps1 → archive/codexcli-bridge.ps1} +0 -0
  249. /package/tools/{gemini-bridge.cmd → archive/gemini-bridge.cmd} +0 -0
  250. /package/tools/{gemini-bridge.sh → archive/gemini-bridge.sh} +0 -0
@@ -123,7 +123,8 @@ The workspace and ledger are shared with superpowers:subagent-driven-development
123
123
  and the new one resumes from the same ledger.
124
124
 
125
125
  - Each plan owns a workspace: at skill start, run
126
- `../subagent-driven-development/scripts/sdd-workspace PLAN_FILE` — it
126
+ `../subagent-driven-development/scripts/sdd-workspace PLAN_FILE` by its
127
+ absolute path, from the working tree you're executing in — it
127
128
  prints the plan's git-ignored directory
128
129
  (`<repo-root>/.superpowers/sdd/<plan-basename>/`), home to every
129
130
  artifact for THIS plan: ledger, briefs, review packages. Another plan's
@@ -169,7 +170,8 @@ in the workspace and read its tail; read a brief, not the whole plan.
169
170
 
170
171
  ### 1. Take the task
171
172
 
172
- - Run this skill's `scripts/task-start PLAN_FILE N`. It prints the brief
173
+ - Run this skill's `scripts/task-start PLAN_FILE N` by its absolute path,
174
+ from the working tree you're executing in. It prints the brief
173
175
  path and BASE (the commit the task's range is cut from) in one call.
174
176
  Read the brief for every task, including ones you remember from setup:
175
177
  what you remember is a summary, the brief has the exact values,
@@ -222,7 +224,7 @@ the claim. If any item is missing, the task is not complete: finish it.
222
224
  ### 4. Complete the task
223
225
 
224
226
  Run this skill's `scripts/task-done PLAN_FILE N BASE -- <test command>`
225
- with the test command the brief names for the whole task. It runs the
227
+ by its absolute path, from the working tree you're executing in, with the test command the brief names for the whole task. It runs the
226
228
  tests, keeps the full output in the workspace, prints the tail, and — only
227
229
  if they pass — appends the completion line to the ledger:
228
230
 
@@ -234,7 +236,7 @@ mark the todo complete and take the next task.
234
236
  ## Final Review
235
237
 
236
238
  Run `../subagent-driven-development/scripts/review-package PLAN_FILE MERGE_BASE HEAD`
237
- (MERGE_BASE = the commit the branch started from, e.g.
239
+ by its absolute path, from the working tree you're executing in (MERGE_BASE = the commit the branch started from, e.g.
238
240
  `git merge-base main HEAD`) and review from the file it prints.
239
241
 
240
242
  **With a subagent tool:** dispatch the reviewer on the most capable
@@ -319,55 +321,3 @@ Use superpowers:finishing-a-development-branch.
319
321
  | "The reviewer said Minor, so it's Minor" | The label graded the spec's silence. Grade what the person gets. Re-grade, then gate. |
320
322
  | "The fix is obvious, no need for a failing test first" | The failing test is the only proof the finding was real and is now gone. Without it you have a diff and a hope. |
321
323
  | "I'll fix the minors too while I'm in there" | Every minor you fix is a test, a fix, and a suite run your partner did not ask for. Ledger them; your partner decides. |
322
-
323
- ## Example Workflow
324
-
325
- ```
326
- You: I'm using the executing-plans skill to implement this plan inline.
327
-
328
- [Setup: worktree verified]
329
- [Read plan once: docs/superpowers/plans/feature-plan.md; spec read]
330
- [Resolve workspace: sdd-workspace docs/superpowers/plans/feature-plan.md — no ledger inside, fresh start]
331
- [Pre-flight scan: 2 shared-interface rows, 4 self-consistency rows, clean; written to ledger]
332
- [Create todos for all tasks]
333
-
334
- Task 1: Hook installation script
335
-
336
- [task-start plan 1 → brief read; BASE a1b2c3d]
337
- [Step 1: write failing test — written]
338
- [Step 2: run it — FAIL: install_hook not defined. Matches Expected.]
339
- [Step 3: implement — written]
340
- [Step 4: run it — PASS 1/1. Matches Expected.]
341
- [Step 5: commit — d4e5f6a]
342
- [Contract: tests ran, output read, no deviations]
343
- [task-done plan 1 a1b2c3d -- npm test -- hooks → ledger: Task 1: complete (commits a1b2c3d..d4e5f6a, tests: npm test -- hooks → 1/1 pass)]
344
-
345
- Task 2: Recovery modes
346
-
347
- [task-start plan 2 → brief read; BASE d4e5f6a]
348
- [Step 2: run failing test — FAIL, but on an import error: Task 1 exported
349
- installHook, brief consumes install_hook]
350
- [Ruling: brief's consumer name is a typo against Task 1's Produces block;
351
- use installHook — Ledger: Task 2: Ruling: install_hook → installHook — matches Task 1 Produces — cost if wrong: one rename]
352
- [Steps 2-5 as planned; commit b7c8d9e]
353
- [task-done plan 2 d4e5f6a -- npm test -- recovery → ledger: Task 2: complete (commits d4e5f6a..b7c8d9e, tests: npm test -- recovery → 8/8 pass)]
354
-
355
- ...
356
-
357
- [After all tasks: review-package plan MERGE_BASE HEAD; dispatch code-reviewer, most capable model]
358
- Reviewer: One Important finding — progress reporting interval hardcoded. Two Minor.
359
- [Re-grade: Important stands; minors → ledger as deferred]
360
- [Fix pass: test_progress_interval_configurable RED → extract PROGRESS_INTERVAL → GREEN; suite 12/12; commit]
361
- [Ledger: Final: fixed hardcoded interval — test_progress_interval_configurable RED→GREEN, suite 12/12]
362
-
363
- Rulings I made:
364
- - Task 2: install_hook → installHook (brief typo; cost if wrong: one rename)
365
-
366
- Deferred minors:
367
- - README lacks a usage example
368
- - recovery.js could split verify/repair into two files
369
-
370
- [Delete this plan's workspace — the record now lives in git]
371
-
372
- Using superpowers:finishing-a-development-branch.
373
- ```
@@ -1,52 +1,52 @@
1
- #!/usr/bin/env bash
2
- # Close one task of an inline plan execution in a single call: run the task's
3
- # test command, keep its full output in the workspace, print the tail, and —
4
- # only if the command succeeded — append the completion line to the ledger.
5
- # A failing command records nothing: the task is not complete.
6
- #
7
- # Usage: task-done PLAN_FILE TASK_NUMBER BASE -- TEST_COMMAND [ARGS...]
8
- # BASE is the SHA task-start printed; the completion line records BASE..HEAD.
9
- # Exit: the test command's exit status.
10
- set -euo pipefail
11
-
12
- if [ $# -lt 5 ] || [ "$4" != "--" ]; then
13
- echo "usage: task-done PLAN_FILE TASK_NUMBER BASE -- TEST_COMMAND [ARGS...]" >&2
14
- exit 2
15
- fi
16
-
17
- plan=$1
18
- n=$2
19
- base=$3
20
- shift 4
21
- sdd="$(cd "$(dirname "$0")/../../subagent-driven-development/scripts" && pwd)"
22
-
23
- git rev-parse --verify --quiet "$base" >/dev/null || { echo "bad BASE: $base" >&2; exit 2; }
24
-
25
- dir=$("$sdd/sdd-workspace" "$plan")
26
- log="$dir/task-${n}-tests.log"
27
- ledger="$dir/progress.md"
28
-
29
- # Render the command the way a person would type it, for the ledger line.
30
- cmd=""
31
- for a in "$@"; do
32
- case "$a" in
33
- *[[:space:]\"\;\|\&]*) cmd="$cmd '$a'" ;;
34
- *) cmd="$cmd $a" ;;
35
- esac
36
- done
37
- cmd=${cmd# }
38
-
39
- rc=0
40
- "$@" > "$log" 2>&1 || rc=$?
41
-
42
- tail -n 5 "$log"
43
- if [ "$rc" -ne 0 ]; then
44
- echo "task-done: test command exited $rc; Task $n NOT recorded (full output: $log)" >&2
45
- exit "$rc"
46
- fi
47
-
48
- last=$(grep -v '^[[:space:]]*$' "$log" | tail -n 1)
49
- [ -f "$ledger" ] || printf '# SDD ledger — plan: %s\n' "$plan" > "$ledger"
50
- line="Task $n: complete (commits $(git rev-parse --short=7 "$base")..$(git rev-parse --short=7 HEAD), tests: $cmd → $last)"
51
- printf '%s\n' "$line" >> "$ledger"
52
- echo "ledger: $line"
1
+ #!/usr/bin/env bash
2
+ # Close one task of an inline plan execution in a single call: run the task's
3
+ # test command, keep its full output in the workspace, print the tail, and —
4
+ # only if the command succeeded — append the completion line to the ledger.
5
+ # A failing command records nothing: the task is not complete.
6
+ #
7
+ # Usage: task-done PLAN_FILE TASK_NUMBER BASE -- TEST_COMMAND [ARGS...]
8
+ # BASE is the SHA task-start printed; the completion line records BASE..HEAD.
9
+ # Exit: the test command's exit status.
10
+ set -euo pipefail
11
+
12
+ if [ $# -lt 5 ] || [ "$4" != "--" ]; then
13
+ echo "usage: task-done PLAN_FILE TASK_NUMBER BASE -- TEST_COMMAND [ARGS...]" >&2
14
+ exit 2
15
+ fi
16
+
17
+ plan=$1
18
+ n=$2
19
+ base=$3
20
+ shift 4
21
+ sdd="$(cd "$(dirname "$0")/../../subagent-driven-development/scripts" && pwd)"
22
+
23
+ git rev-parse --verify --quiet "$base" >/dev/null || { echo "bad BASE: $base" >&2; exit 2; }
24
+
25
+ dir=$("$sdd/sdd-workspace" "$plan")
26
+ log="$dir/task-${n}-tests.log"
27
+ ledger="$dir/progress.md"
28
+
29
+ # Render the command the way a person would type it, for the ledger line.
30
+ cmd=""
31
+ for a in "$@"; do
32
+ case "$a" in
33
+ *[[:space:]\"\;\|\&]*) cmd="$cmd '$a'" ;;
34
+ *) cmd="$cmd $a" ;;
35
+ esac
36
+ done
37
+ cmd=${cmd# }
38
+
39
+ rc=0
40
+ "$@" > "$log" 2>&1 || rc=$?
41
+
42
+ tail -n 5 "$log"
43
+ if [ "$rc" -ne 0 ]; then
44
+ echo "task-done: test command exited $rc; Task $n NOT recorded (full output: $log)" >&2
45
+ exit "$rc"
46
+ fi
47
+
48
+ last=$(grep -v '^[[:space:]]*$' "$log" | tail -n 1) || last="(no output)"
49
+ [ -f "$ledger" ] || printf '# SDD ledger — plan: %s\n' "$plan" > "$ledger"
50
+ line="Task $n: complete (commits $(git rev-parse --short=7 "$base")..$(git rev-parse --short=7 HEAD), tests: $cmd → $last)"
51
+ printf '%s\n' "$line" >> "$ledger"
52
+ echo "ledger: $line"
@@ -1,28 +1,28 @@
1
- #!/usr/bin/env bash
2
- # Begin one task of an inline plan execution in a single call: extract the
3
- # task's brief (via subagent-driven-development's task-brief, so both skills
4
- # share one workspace) and record BASE, the commit the task's review range is
5
- # cut from. One tool call instead of two, because every call in an inline
6
- # session is a turn that re-reads the whole context.
7
- #
8
- # Usage: task-start PLAN_FILE TASK_NUMBER
9
- # Prints:
10
- # brief: <path to the task's brief file>
11
- # base: <full SHA of HEAD>
12
- set -euo pipefail
13
-
14
- if [ $# -ne 2 ]; then
15
- echo "usage: task-start PLAN_FILE TASK_NUMBER" >&2
16
- exit 2
17
- fi
18
-
19
- plan=$1
20
- n=$2
21
- sdd="$(cd "$(dirname "$0")/../../subagent-driven-development/scripts" && pwd)"
22
-
23
- out=$("$sdd/task-brief" "$plan" "$n")
24
- brief=$(printf '%s\n' "$out" | sed -n 's/^wrote \(.*\): [0-9][0-9]* lines$/\1/p')
25
- [ -n "$brief" ] || { echo "task-brief did not report a path: $out" >&2; exit 1; }
26
-
27
- echo "brief: $brief"
28
- echo "base: $(git rev-parse HEAD)"
1
+ #!/usr/bin/env bash
2
+ # Begin one task of an inline plan execution in a single call: extract the
3
+ # task's brief (via subagent-driven-development's task-brief, so both skills
4
+ # share one workspace) and record BASE, the commit the task's review range is
5
+ # cut from. One tool call instead of two, because every call in an inline
6
+ # session is a turn that re-reads the whole context.
7
+ #
8
+ # Usage: task-start PLAN_FILE TASK_NUMBER
9
+ # Prints:
10
+ # brief: <path to the task's brief file>
11
+ # base: <full SHA of HEAD>
12
+ set -euo pipefail
13
+
14
+ if [ $# -ne 2 ]; then
15
+ echo "usage: task-start PLAN_FILE TASK_NUMBER" >&2
16
+ exit 2
17
+ fi
18
+
19
+ plan=$1
20
+ n=$2
21
+ sdd="$(cd "$(dirname "$0")/../../subagent-driven-development/scripts" && pwd)"
22
+
23
+ out=$("$sdd/task-brief" "$plan" "$n")
24
+ brief=$(printf '%s\n' "$out" | sed -n 's/^wrote \(.*\): [0-9][0-9]* lines$/\1/p')
25
+ [ -n "$brief" ] || { echo "task-brief did not report a path: $out" >&2; exit 1; }
26
+
27
+ echo "brief: $brief"
28
+ echo "base: $(git rev-parse HEAD)"
@@ -1,23 +1,11 @@
1
1
  ---
2
2
  name: gemini-collaborator
3
- description: Coordinate with Google Antigravity / Gemini CLI (agy.exe) to cross-validate changes, request second opinions on architecture/diffs, or execute adversarial code reviews.
3
+ description: Coordinate with Google Antigravity / Gemini CLI (agy.exe) via Herdr to cross-validate changes, request second opinions on architecture/diffs, or execute adversarial code reviews.
4
4
  ---
5
5
 
6
6
  # Gemini Collaborator Skill
7
7
 
8
- This skill enables Claude Code to orchestrate tasks with Google Antigravity / Gemini CLI (`agy.exe`), delegating complex architectural reasoning, diff reviews, codebase scans, and adversarial validation.
9
-
10
- ## Real-Time Visibility in Herdr (Right Split & Auto-Close)
11
-
12
- By default when running inside Herdr, all bridge invocations automatically:
13
- - **Split the calling screen to the right**: Creates a side-by-side split pane in your current Herdr window.
14
- - **Display a prominent request banner**:
15
- - Caller AI $\rightarrow$ Target Model (Claude Code $\rightarrow$ Antigravity / Gemini)
16
- - Action & Working Directory
17
- - **`>> WHAT IS BEING REQUESTED:`** A highlighted box showing the exact prompt/instructions.
18
- - Summary of modified files (`git diff --stat`) for code reviews.
19
- - **Stream Gemini's live execution**: Real-time display of reasoning, tool calls, and output right in that split pane.
20
- - **Auto-close when complete**: Automatically closes the right pane after finishing and collapses your screen back to normal, returning the captured output to Claude Code.
8
+ This skill enables Claude Code to orchestrate tasks with Google Antigravity / Gemini CLI (`agy.exe`) directly through native Herdr multiplexing, delegating complex architectural reasoning, diff reviews, codebase scans, and adversarial validation.
21
9
 
22
10
  ## When to Activate
23
11
 
@@ -25,59 +13,39 @@ By default when running inside Herdr, all bridge invocations automatically:
25
13
  - After making non-trivial code edits or architectural refactors, to verify there are no hidden regressions from Gemini's perspective.
26
14
  - When facing ambiguous design choices where Gemini's large context window and deep multi-perspective reasoning help pick the best approach.
27
15
 
28
- ## Available Actions via `tools/gemini-bridge.ps1`
16
+ ## Orchestration Method: Native Herdr Agent (`herdr` skill)
29
17
 
30
- Run commands using the project PowerShell helper script:
18
+ When running inside Herdr (`$env:HERDR_ENV = "1"`), communicate directly using Herdr's native agent orchestration. This maintains a persistent session across turns, preserves context, respects interactive approvals (`blocked`), and handles bracketed paste:
31
19
 
32
- ### 1. Adversarial Code Review of Git Diff
33
- Splits the screen to the right, runs Antigravity review, streams live, and auto-closes:
34
- ```powershell
35
- powershell -ExecutionPolicy Bypass -File tools/gemini-bridge.ps1 review
20
+ ### 1. Fast Path: Re-use Active Idle Agent
21
+ Before splitting a pane, check if a Gemini/Antigravity agent is already running and idle:
22
+ ```bash
23
+ herdr agent list
36
24
  ```
37
- To provide specific review instructions:
38
- ```powershell
39
- powershell -ExecutionPolicy Bypass -File tools/gemini-bridge.ps1 review "Focus on security vulnerabilities, memory leaks, and concurrency edge cases"
25
+ If an agent named `gemini-reviewer` or `agy` is idle or done, prompt it directly:
26
+ ```bash
27
+ herdr agent prompt gemini-reviewer "Review the latest changes." --wait --timeout 120000
40
28
  ```
41
29
 
42
- ### 2. Consult Gemini for Architectural Second Opinion
43
- Sends an inquiry or architectural prompt directly to Gemini in a right-split pane:
44
- ```powershell
45
- powershell -ExecutionPolicy Bypass -File tools/gemini-bridge.ps1 ask "How should we structure this module's caching and database connection pooling?"
30
+ ### 2. Spawning a New Gemini Agent (Single-Execution Batch)
31
+ If no active Gemini agent exists, batch pane creation and agent startup in a single command:
32
+ ```bash
33
+ PANE_ID=$(herdr pane split --current --direction right --cwd "$PWD" --no-focus | jq -r '.result.pane.pane_id')
34
+ herdr agent start gemini-reviewer --kind agy --pane "$PANE_ID"
35
+ herdr agent prompt gemini-reviewer "Review git diff for security regressions and type errors." --wait --timeout 120000
46
36
  ```
47
37
 
48
- ### 3. Scan Monorepo or Codebase
49
- Instructs Gemini to scan the repository for specific patterns or consistency with doctrine:
50
- ```powershell
51
- powershell -ExecutionPolicy Bypass -File tools/gemini-bridge.ps1 scan "Find all authentication token refresh and session handling references"
38
+ ### 3. Read Findings into Context
39
+ ```bash
40
+ herdr agent read gemini-reviewer --source recent-unwrapped --lines 120
52
41
  ```
53
42
 
54
- ### 4. Interactive Handoff to Gemini in a Right Split Pane
55
- Launches a full interactive Antigravity CLI session in a right split pane pre-loaded with a task:
56
- ```powershell
57
- powershell -ExecutionPolicy Bypass -File tools/gemini-bridge.ps1 interactive "Let's refactor the data access layer together"
43
+ ### 4. Interactive Collaboration
44
+ When an interactive session or clarification is needed, send keys or prompt interactively:
45
+ ```bash
46
+ herdr agent send-keys gemini-reviewer enter
58
47
  ```
59
48
 
60
- ### Display & Control Flags:
61
- - *(default)*: Splits the current Herdr screen to the right, streams live, and auto-closes when done.
62
- - `-KeepOpen`: Keeps the split pane open after completion instead of auto-closing.
63
- - `-Tab`: Opens in a new Herdr tab instead of splitting the screen.
64
- - `-Window`: Forces a standalone OS console window instead of Herdr.
65
- - `-Headless`: Runs silently in the background (invokes `agy -p` directly).
66
- - `-NoFocus`: Prevents switching focus to the right pane.
67
- - `-Timeout <seconds>`: Custom timeout in seconds (default: 300).
68
-
69
- ## Fallback Direct CLI Invocations (Headless / Standalone)
70
-
71
- If `tools/gemini-bridge.ps1` is not present in the workspace, Claude Code can invoke `agy` directly from the terminal:
72
- - **Headless prompt**:
73
- ```powershell
74
- agy --dangerously-skip-permissions -p "Review the latest changes in git diff and identify potential regressions."
75
- ```
76
- - **Interactive session**:
77
- ```powershell
78
- agy --dangerously-skip-permissions -i "Let's work through this problem together."
79
- ```
80
-
81
49
  ## Guidelines for Claude Code
82
50
 
83
51
  - **Synthesize, Don't Blindly Echo**: When Gemini returns feedback, analyze its critiques against the project's requirements, architectural documentation, and existing patterns.
@@ -0,0 +1,65 @@
1
+ ---
2
+ name: grill-me
3
+ description: Relentlessly interview the user to stress-test and sharpen a plan, architecture, or design before implementation. Use when planning features, resolving tradeoffs, or when the user invokes /grill-me.
4
+ ---
5
+
6
+ # The Grilling Protocol (Stress-Test & Sharpen Plans)
7
+
8
+ Interview the user relentlessly until you reach an airtight shared understanding. Map the problem space as a **design tree**: every decision branches into the decisions that hang off it.
9
+
10
+ ---
11
+
12
+ ## 1. The Design Tree Frontier (Round-by-Round)
13
+
14
+ Work the design tree in **rounds**.
15
+ - The **frontier** is every decision whose prerequisites are already settled: the questions you can ask *now* without guessing at answers you haven't heard yet.
16
+ - Ask the whole frontier in one round: number each question and provide your concrete recommendation.
17
+ - **Dependency Rule**: If Question B depends on the choice made in Question A, Question B does NOT belong in this round. It belongs in a *subsequent* round once Question A is resolved.
18
+
19
+ ---
20
+
21
+ ## 2. The "Yes-to-Approve" Triage Format
22
+
23
+ Always format questions so the user can quickly accept your recommendations with minimal keystrokes (e.g. replying *"1: yes, 2: yes, 3: no do Y"*):
24
+
25
+ ```markdown
26
+ ❓ **Q1 - <Decision Title>**: <Context, boundary conditions, edge cases, and options>
27
+
28
+ ➡️ **Recommended**: <Your recommended answer and justification>
29
+
30
+ ---
31
+
32
+ ❓ **Q2 - <Decision Title>**: <Context, boundary conditions, edge cases, and options>
33
+
34
+ ➡️ **Recommended**: <Your recommended answer and justification>
35
+ ```
36
+
37
+ **Rule**: Word each question and recommendation so answering *"yes"* or *"accept"* selects your recommended path.
38
+
39
+ ---
40
+
41
+ ## 3. Autonomous Fact-Finding Invariant (Zero Lazy Questions)
42
+
43
+ **Finding facts is your job, never the user's.**
44
+ - If a question hinges on a fact from the repository (e.g., existing middleware, schema types, installed package versions, API endpoints, config flags):
45
+ - **Look it up autonomously** using filesystem tools, greps, and doc inspections before asking.
46
+ - Never ask the user for anything you can discover yourself.
47
+ - Only present decisions, requirements, and business trade-offs that cannot be answered by the code.
48
+
49
+ ---
50
+
51
+ ## 4. ADR & Documentation Integration
52
+
53
+ When grilling uncovers settled architectural decisions for significant or multi-system features:
54
+ - Record each settled decision in an **Architectural Decision Record (ADR)** under `docs/adr/YYYY-MM-DD-<decision>.md` (or the project's designated ADR directory).
55
+ - Keep ADRs compact: Context, Decision, Invariants, Consequences.
56
+ - Maintain consistent domain terminology in the project's domain docs or glossary.
57
+
58
+ ---
59
+
60
+ ## 5. Exit Criteria
61
+
62
+ The grilling session is complete when:
63
+ 1. The decision frontier is empty (all branches visited, zero hidden assumptions).
64
+ 2. The user has confirmed the proposed recommendations or made their adjustments.
65
+ 3. The agreed scope is ready to be compiled into a specification or plan (`to-spec` / `writing-plans` / `05-canonical-plan-template.md`).
@@ -0,0 +1,64 @@
1
+ ---
2
+ name: handoff
3
+ description: Compact the current conversation and session context into an isolated handoff document so a fresh agent or subagent can pick up work without drift.
4
+ ---
5
+
6
+ # The Handoff Protocol
7
+
8
+ When ending a session, switching agent contexts, or spawning a fresh child agent (e.g. via `invoke_subagent`, `herdr`, or `claude --bg`), create a lean, structured handoff document.
9
+
10
+ ---
11
+
12
+ ## 1. Zero-Duplication & Pointer-First Principle
13
+
14
+ Do **not** dump raw source code, large file bodies, verbose conversational histories, or full plan duplicates into the handoff artifact.
15
+ - **Reference existing artifacts by path or commit hash**:
16
+ - Plan / Spec: `docs/designs/YYYY-MM-DD-<feature>.md`
17
+ - ADRs: `docs/adr/`
18
+ - Git branch & diff: `feature/xyz` (`git diff origin/main..HEAD`)
19
+ - Failing test paths: `tests/integration/...`
20
+ - **Redact secrets**: Strip API keys, session tokens, or sensitive credentials.
21
+
22
+ ---
23
+
24
+ ## 2. Storage Location
25
+
26
+ Write the handoff file to the operating system's temporary directory to avoid polluting the git working tree:
27
+ - **Windows**: `$env:TEMP\handoff-<feature>-<timestamp>.md` (e.g. `C:\Users\<user>\AppData\Local\Temp\...`)
28
+ - **Linux / macOS**: `/tmp/handoff-<feature>-<timestamp>.md`
29
+
30
+ ---
31
+
32
+ ## 3. Mandatory Document Structure
33
+
34
+ A handoff document must follow this template:
35
+
36
+ ```markdown
37
+ # Session Handoff: <Feature or Task Name>
38
+
39
+ ### 1. Status & Blast Radius
40
+ - **Current State**: [WIP / Blocked / Ready for Verification / Awaiting Review]
41
+ - **Target Branch**: `<branch-name>`
42
+ - **Last Verified Commit**: `<short-hash>` (or unstaged changes in working copy)
43
+
44
+ ### 2. Settled Decisions & Pointers
45
+ - **Spec / Plan**: [docs/designs/YYYY-MM-DD-feature.md](file:///path/to/spec)
46
+ - **ADR**: [docs/adr/...](file:///path/to/adr)
47
+ - **Decided Invariants**: <1-2 bullet summary of settled boundaries>
48
+
49
+ ### 3. Open Frontier & Next Immediate Actions
50
+ 1. <Exact first command or test to execute>
51
+ 2. <Expected failure or next component to modify>
52
+
53
+ ### 4. Suggested Skills for Next Agent
54
+ - `<skill-name-1>`: <Why the next agent should call this skill>
55
+ - `<skill-name-2>`: <Why the next agent should call this skill>
56
+ ```
57
+
58
+ ---
59
+
60
+ ## 4. Seeding the Next Agent
61
+
62
+ - **Antigravity / Subagent**: Launch the subagent with the handoff path or concise summary containing the pointer.
63
+ - **Claude Code CLI**: Run `claude --bg --name "<Task Name>" -- "$(cat <path-to-temp-handoff>)"`. Passing via file keeps the shell from misinterpreting special characters (`$`, backticks).
64
+ - **Herdr Multiplexing**: Seed the target agent pane via `herdr agent prompt <agent> "..."`.