6 Commits

Author	SHA1	Message	Date
John Lindquist	8e24d0694a	feat: add chainTo skill chaining, prompt signals, validation upgrades, and dedup reset on context clear ... Add a chainTo frontmatter field to skills that triggers follow-up skill injection when PostToolUse file contents match regex patterns. Add upgradeToSkill/upgradeWhy fields to validation rules so validate errors can recommend loading a specific skill. Register posttooluse-bash-chain.mjs in hooks.json. Add ChainToRule interface to patterns.mts and skill-map-frontmatter.mts, with parseChainToRules() parser. Add duplicate-key detection to the YAML parser. Reset dedup claim dir and session file on clear/compact events in session-start-seen-skills so skills re-inject into fresh context windows. Add chainTo rules to: agent-browser-verify, agent-browser, ai-elements, ai-gateway, ai-generation-persistence, ai-sdk, auth, bootstrap, chat-sdk, cms, cron-jobs, deployments-cicd, email, env-vars, geist, investigation-mode, json-render, marketplace, micro, ncc, next-forge, nextjs, observability, payments, react-best-practices, routing-middleware, runtime-cache, satori, shadcn, sign-in-with-vercel, swr, turbopack, turborepo, v0-dev, vercel-agent, vercel-api, vercel-cli, vercel-firewall, vercel-flags, vercel-functions, vercel-queues, vercel-sandbox, vercel-storage, verification, workflow. Add upgradeToSkill to ai-elements and ai-sdk validate rules. Expand ai-sdk validate messages with Run Skill() hints. Update nextjs, vercel-storage, runtime-cache, workflow, turborepo skill bodies. Add new skills: geistdocs (Geist design system docs), zzz-test-meta-name-mask (test fixture). Add skills/_chain-audit.md chain coverage audit doc. Delete .claude-plugin/marketplace.json, .claude-plugin/plugin.json (deprecated), skills/edge-runtime/SKILL.md (consolidated into vercel-functions). Add tests: posttooluse-chain.test.ts (4699 lines, chain injection e2e), ai-sdk-companion.test.ts (181 lines). Expand build-skill-map.test.ts (+335 lines), validate-rules.test.ts (+936 lines), session-start-seen-skills.test.ts (+74 lines), skill-map-frontmatter.test.ts (+50 lines), verification-skill.test.ts (+20 lines). Update build-manifest.ts to emit chainTo rules and upgradeToSkill fields. Rebuild generated/skill-manifest.json, generated/skill-catalog.md, generated/build-from-skills.manifest.json. Rebuild all compiled hooks/*.mjs. Update CLAUDE.md lexical prompt default to on. Update vercel.md ecosystem graph, docs, and cli-reference.	2026-03-11 15:18:35 -06:00
John Lindquist	b8b233995c	feat(skills): broaden trigger patterns for 7 under-injected skills based on eval findings; add next-forge skill; bump to 0.15.0 ... Eval analysis of 9 real sessions showed 10 skills never triggering despite being requested. Root causes: pathPatterns too narrow (agents write to lib/email-template.tsx not emails/), promptSignals containing regex instead of plain text (vercel-sandbox), and missing promptSignals entirely (v0-dev, vercel-firewall). Skills updated: email, vercel-queues, edge-runtime, vercel-firewall, chat-sdk, v0-dev, vercel-sandbox. New skill: next-forge (bootstrap detection).	2026-03-09 17:56:23 -06:00
John Lindquist	0c49abc547	fix(skills): quote YAML validate patterns ending with colon to fix js-yaml parse errors; bump to 0.14.1	2026-03-09 16:38:11 -06:00
John Lindquist	1dfa612df7	feat(hooks): observe agent subagent spawns ... Add a PreToolUse observer hook that records Agent tool launches as pending subagent spawn metadata for downstream bootstrap logic. It preserves the existing no-mutation contract by always returning {} and now integrates with the committed subagent-state append API. Verified: bun test tests/pretooluse-subagent-spawn-observe.test.ts Verified: ./node_modules/.bin/tsc -p hooks/tsconfig.json --noEmit How to test: run bun test tests/pretooluse-subagent-spawn-observe.test.ts Swarm-Agent: codex-observer	2026-03-09 16:28:50 -06:00
John Lindquist	2f8111da6d	feat(subagent-state): add pending launch state helpers ... Add a shared hooks library for pending subagent launch records and per-agent JSON state. The module filters stale launch records, claims the oldest matching launch under a file lock, and writes agent state with atomic rename semantics. Verified: bun test tests/subagent-state.test.ts Verified: node --input-type=module -e "import('./hooks/subagent-state.mjs').then((mod) => { if (typeof mod.listPendingLaunches !== 'function' || typeof mod.claimPendingLaunch !== 'function' || typeof mod.appendPendingLaunch !== 'function' || typeof mod.readAgentState !== 'function' || typeof mod.writeAgentState !== 'function') { process.exit(1); } })" Swarm-Agent: codex-subagent-state	2026-03-09 16:25:50 -06:00
John Lindquist	92dbe3ae02	feat(hooks): add SubagentStart/SubagentStop hooks for subagent skill injection; bump to 0.14.0 ... - SubagentStart bootstrap hook injects project context (likely skills, summaries) into spawned subagents with budget scaling by agent type (minimal for Explore/Plan, standard for general-purpose) - SubagentStop sync hook writes agent metadata to a session-scoped JSONL ledger for observability - SessionEnd cleanup extended to remove subagent ledger files - Updated ai-elements/nextjs skills, benchmark-agents and eval skill definitions	2026-03-09 15:52:56 -06:00