session-orchestrator 5.1.0 → 5.3.0

package/.agents/skills/architecture/SKILL.md

@@ -10,9 +10,11 @@ metadata:
 
 # architecture
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/architecture/SKILL.md`](../../../skills/architecture/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/autopilot/SKILL.md

@@ -3,15 +3,20 @@ name: autopilot
 description: "Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with all 10 kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, max-sessions, resource-overload, token-budget, stall-timeout, sub-threshold confidence, user-abort). Reads Mode-Selector output (Phase B) to decide auto-execute vs. fallback. Writes one autopilot.jsonl record per loop run. Phase C scaffold (issue #277); implementation lives in scripts/lib/autopilot.mjs (Phase C-1 follow-up)."
 metadata:
   user-invocable: "true"
+  argument-hint: "[--headless] [--verbose] [--max-sessions=N] [--max-hours=H] [--confidence-threshold=0.X] [--dry-run]"
   tags: phase-c, autopilot, autonomous, loop
   model: sonnet
 ---
 
 # autopilot
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/autopilot/SKILL.md`](../../../skills/autopilot/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/autopilot/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: autopilot
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/bootstrap/SKILL.md

@@ -3,6 +3,8 @@ name: bootstrap
 description: "Use this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked automatically by the Bootstrap Gate when CLAUDE.md, Session Config, or bootstrap.lock is missing. Also available as /bootstrap for manual invocation. Three intensity tiers: fast (demos/spikes), standard (MVPs), deep (production/team)."
 metadata:
   user-invocable: "true"
+  disable-model-invocation: "true"
+  argument-hint: "[--upgrade <tier>]"
   tags: bootstrap, setup, scaffold, init
   model: sonnet
   model-preference: sonnet
@@ -12,9 +14,13 @@ metadata:
 
 # bootstrap
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/bootstrap/SKILL.md`](../../../skills/bootstrap/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/bootstrap/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: bootstrap
+policy:
+  allow_implicit_invocation: false

package/.agents/skills/brainstorm/SKILL.md

@@ -4,6 +4,9 @@ description: Use when you have a feature idea but the scope or UX is still ambig
 metadata:
   model: inherit
   color: cyan
+  user-invocable: "true"
+  disable-model-invocation: "true"
+  argument-hint: "[topic-or-feature-slug]"
 allowed-tools:
   - Read
   - Grep
@@ -14,9 +17,13 @@ allowed-tools:
 
 # brainstorm
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/brainstorm/SKILL.md`](../../../skills/brainstorm/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/brainstorm/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: brainstorm
+policy:
+  allow_implicit_invocation: false

package/.agents/skills/claude-md-drift-check/SKILL.md

@@ -7,9 +7,11 @@ metadata:
 
 # claude-md-drift-check
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/claude-md-drift-check/SKILL.md`](../../../skills/claude-md-drift-check/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/close/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: close
+description: End session with verification, commits, and documentation
+metadata:
+  user-invocable: "true"
+  disable-model-invocation: "true"
+  model: inherit
+---
+
+# close
+
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
+> [`skills/close/SKILL.md`](../../../skills/close/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/close/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: close
+policy:
+  allow_implicit_invocation: false

package/.agents/skills/convergence-monitoring/SKILL.md

@@ -2,7 +2,7 @@
 name: convergence-monitoring
 description: "Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive a Stop/Continue/Investigate decision at each inter-wave checkpoint. Distinct from /evolve (retrospective) and session-reviewer (wave output review): convergence-monitoring answers \"are we making progress?\" not \"was the last wave correct?\". Primary consumer: /autoresearch loops and wave-executor inter-wave checkpoints."
 metadata:
-  user-invocable: "true"
+  user-invocable: "false"
   tags: autoresearch, convergence, loop-control, wave-executor
   model: haiku
   model-preference: sonnet
@@ -14,9 +14,11 @@ metadata:
 
 # convergence-monitoring
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/convergence-monitoring/SKILL.md`](../../../skills/convergence-monitoring/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/debug/SKILL.md

@@ -4,6 +4,8 @@ description: "Use when encountering any bug, test failure, build break, or unexp
 metadata:
   model: inherit
   color: red
+  user-invocable: "true"
+  argument-hint: "[bug-description-or-issue-ref]"
 allowed-tools:
   - Read
   - Grep
@@ -14,9 +16,13 @@ allowed-tools:
 
 # debug
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/debug/SKILL.md`](../../../skills/debug/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/debug/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: debug
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/discovery/SKILL.md

@@ -2,7 +2,8 @@
 name: discovery
 description: Use this skill when running systematic quality discovery and issue detection. Runs modular probes adapted to the project's tech stack, presents findings interactively for user triage, and creates VCS issues for confirmed problems. Invoked standalone via /discovery or embedded in session-end.
 metadata:
-  user-invocable: "false"
+  user-invocable: "true"
+  argument-hint: "[all|code|infra|ui|arch|session|audit|vault|feature] [--since <git-ref>] [--full]"
   tags: quality, discovery, probes, issues
   model: sonnet
   model-preference: sonnet
@@ -12,9 +13,13 @@ metadata:
 
 # discovery
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/discovery/SKILL.md`](../../../skills/discovery/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/discovery/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: discovery
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/dispatcher/SKILL.md

@@ -2,14 +2,20 @@
 name: dispatcher
 description: "Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one via AskUserQuestion, atomically claims it, and routes you to the chosen entry command. Triggers: \"what should I work on next\", \"dispatch me to a repo\", \"pick the next project\", \"run /dispatcher\". <example>Context: operator finished a session and wants the next-best repo across the portfolio. user: \"/dispatcher\" assistant: \"Ranked 18 free repos — top recommendation: Pencil-Designs (score 4.50, 90d stale). Confirm via the picker, I'll claim its lease atomically, then route you to /session deep.\"</example>"
 metadata:
+  user-invocable: "true"
+  argument-hint: "[--dry-run] [--repo <name>]"
   model: sonnet
 ---
 
 # dispatcher
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/dispatcher/SKILL.md`](../../../skills/dispatcher/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/dispatcher/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: dispatcher
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/docs-orchestrator/SKILL.md

@@ -10,9 +10,11 @@ metadata:
 
 # docs-orchestrator
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/docs-orchestrator/SKILL.md`](../../../skills/docs-orchestrator/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/ecosystem-health/SKILL.md

@@ -12,9 +12,11 @@ metadata:
 
 # ecosystem-health
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/ecosystem-health/SKILL.md`](../../../skills/ecosystem-health/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/eli5/SKILL.md

@@ -2,6 +2,8 @@
 name: eli5
 description: Explain a topic like I'm a 5 year old — restate my last output, or a named topic, in plain words without dropping a single fact. Use when the user types /eli5 [topic], or says an answer was too technical, too long, or unclear about what he now has to do.
 metadata:
+  user-invocable: "true"
+  argument-hint: "[topic]"
   model: inherit
 allowed-tools:
   - Read
@@ -12,9 +14,13 @@ allowed-tools:
 
 # eli5
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/eli5/SKILL.md`](../../../skills/eli5/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/eli5/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: eli5
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/eval/SKILL.md

@@ -1,8 +1,9 @@
 ---
 name: eval
-description: Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v1 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first with an optional advisory LLM judge; never produces a global score.
+description: Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v2 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first with an optional advisory LLM judge; never produces a global score.
 metadata:
   user-invocable: "true"
+  argument-hint: "[--session <id>] [--no-write] [--verify <run-id>]"
   tags: eval, measurement, quality, meta, standard
   model: sonnet
   model-preference: sonnet
@@ -13,9 +14,13 @@ metadata:
 
 # eval
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/eval/SKILL.md`](../../../skills/eval/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/eval/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: eval
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/evolve/SKILL.md

@@ -2,20 +2,25 @@
 name: evolve
 description: "Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl."
 metadata:
-  user-invocable: "false"
+  user-invocable: "true"
+  argument-hint: "[analyze|review|list|dialectic [--apply]]"
   tags: learning, intelligence, meta
   model: sonnet
   model-preference: sonnet
   model-preference-codex: gpt-5.4-mini
   model-preference-cursor: claude-sonnet-4-6
-  args-schema: "[{\"flag\":\"--apply\",\"description\":\"Apply dialectic-derived diff to USER.md + AGENT.md\"},{\"flag\":\"--dry-run\",\"description\":\"Show diff without writing (default)\"},{\"flag\":\"--model <name>\",\"description\":\"Override single-pass LLM (haiku|sonnet|opus)\"},{\"flag\":\"--budget-tokens <N>\",\"description\":\"Token budget for derivation prompt (default 8000)\"}]"
+  args-schema: "[{\"flag\":\"--apply\",\"description\":\"Apply dialectic-derived diff to USER.md + AGENT.md\"},{\"flag\":\"--dry-run\",\"description\":\"Show diff without writing (default)\"},{\"flag\":\"--model <name>\",\"description\":\"Override single-pass LLM (haiku|sonnet|opus)\"},{\"flag\":\"--budget-tokens <N>\",\"description\":\"Input token ceiling for derivation prompt (default 32000; aborts above it, never truncates)\"}]"
 ---
 
 # evolve
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/evolve/SKILL.md`](../../../skills/evolve/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/evolve/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: evolve
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/frontmatter-guard/SKILL.md

@@ -7,9 +7,11 @@ metadata:
 
 # frontmatter-guard
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/frontmatter-guard/SKILL.md`](../../../skills/frontmatter-guard/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/gitlab-ops/SKILL.md

@@ -12,9 +12,11 @@ metadata:
 
 # gitlab-ops
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/gitlab-ops/SKILL.md`](../../../skills/gitlab-ops/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/gitlab-portfolio/SKILL.md

@@ -7,9 +7,11 @@ metadata:
 
 # gitlab-portfolio
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/gitlab-portfolio/SKILL.md`](../../../skills/gitlab-portfolio/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/go/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: go
+description: Approve session plan and begin wave execution
+metadata:
+  user-invocable: "true"
+  disable-model-invocation: "true"
+  argument-hint: "[optional instructions]"
+  model: inherit
+---
+
+# go
+
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
+> [`skills/go/SKILL.md`](../../../skills/go/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/go/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: go
+policy:
+  allow_implicit_invocation: false

package/.agents/skills/grill/SKILL.md

@@ -2,6 +2,8 @@
 name: grill
 description: Use when the user wants a plan, design, or PRD stress-tested before any build — relentlessly interrogates one decision at a time, grounds every question in the codebase, hunts contradictions against the domain language and the code, and challenges the load-bearing assumptions. Triggered by "grill me", "stress-test this plan", "poke holes in my design". Composable — run standalone or as an adversarial pass before /plan feature.
 metadata:
+  user-invocable: "true"
+  argument-hint: "[file-path-or-topic]"
   model: inherit
   color: red
 allowed-tools:
@@ -14,9 +16,13 @@ allowed-tools:
 
 # grill
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/grill/SKILL.md`](../../../skills/grill/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/grill/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: grill
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/harness-audit/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: harness-audit
+description: Run the harness audit and report the rubric score for this repository
+metadata:
+  user-invocable: "true"
+  model: inherit
+---
+
+# harness-audit
+
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
+> [`skills/harness-audit/SKILL.md`](../../../skills/harness-audit/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/harness-audit/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: harness-audit
+policy:
+  allow_implicit_invocation: true

package/.agents/skills/hook-development/SKILL.md

@@ -7,9 +7,11 @@ metadata:
 
 # hook-development
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/hook-development/SKILL.md`](../../../skills/hook-development/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/mcp-builder/SKILL.md

@@ -7,9 +7,11 @@ metadata:
 
 # mcp-builder
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/mcp-builder/SKILL.md`](../../../skills/mcp-builder/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.agents/skills/memory-cleanup/SKILL.md

@@ -3,6 +3,7 @@ name: memory-cleanup
 description: Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under ~/.claude/projects/*/memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke with /memory-cleanup.
 metadata:
   user-invocable: "true"
+  argument-hint: "[--dry-run | --apply-pending]"
   tags: memory, maintenance, meta, dream
   model: sonnet
   model-preference: sonnet
@@ -13,9 +14,13 @@ metadata:
 
 # memory-cleanup
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow lives at
 > [`skills/memory-cleanup/SKILL.md`](../../../skills/memory-cleanup/SKILL.md); read that file for the full instructions.
 > This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
 > discover skills under `.agents/skills/` can find and route to the skill.
 >
 > Regenerate with `node scripts/generate-agents-skills.mjs`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. Pass command arguments through structured tool parameters or safely quoted individual arguments.

package/.agents/skills/memory-cleanup/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-agents-skills.mjs; do not edit.
+interface:
+  display_name: memory-cleanup
+policy:
+  allow_implicit_invocation: true