fix(plugin): fix hooks and add missing skills for reliable skill invocation (#227 )

* fix: overhaul Claude Code plugin for correctness and spec compliance

- Fix critical bugs: coder-agent name (CoderAgent→coder-agent), manifest
  path in session-start.sh, /oac:setup ghost command replaced with /install-context
- Fix hooks.json: add timeout/async, add description, restore matcher
- Fix session-start.sh: dual-format output (Claude Code + Cursor/OpenCode),
  remove invalid JSON escapes for $ and backtick
- Fix agent spec compliance: disallowedTools on read-only agents, WebFetch
  on external-scout, haiku model on context-scout, example blocks on 3 agents
- Fix skill descriptions: triggering conditions only (no workflow summaries)
  per superpowers empirical testing — prevents Claude shortcutting skill content
- Add Red Flags + Rationalization tables to 4 discipline skills
- Add install-context skill + command replacing oac-setup/oac-plan/oac-add-context
- Add cleanup-tmp.sh (was missing, broke /oac:cleanup)
- Add TypeScript installer (install-context.ts/js) with profile-based download
- Update plugin.json: keywords, homepage for marketplace discoverability
- Update README: correct skill count, fix structure diagram, remove stale refs
- Remove obsolete files: FIRST-TIME-SETUP.md, INSTALL.md, QUICK-START.md,
  download-context.sh, verify-context.sh, load-config.sh, context-manager skill,
  oac-setup/oac-plan/oac-add-context commands

* add TypeScript and OpenCode context standards files

Adds three new context files covering universal TypeScript patterns,
OpenCode-specific patterns (fn() wrapper, namespaces, Instance.state()),
and context-system-specific TypeScript coding standards.

* fix(plugin): fix hooks and add missing skills for reliable skill invocation

- Rewrite using-oac skill with always-on skill-check rule (was conditional on dev task detection)
- Update session-start.sh to dynamically inject full skill catalogue at session start
- Add brainstorming skill: intercepts creative/build work before any implementation
- Add systematic-debugging skill: 4-phase root cause process before any fix
- Add verification-before-completion skill: evidence-before-claims gate
- Add /brainstorm and /debug slash commands as pure skill shortcuts
- Fix oac-help to use disable-model-invocation:true (pure shortcut, not self-rendering)
- Fix oac-status to be simpler bash-based status check

2026-02-19 21:12:20 +00:00

3.2 KiB

Raw Blame History

name	description
verification-before-completion	Use when about to claim work is complete, fixed, or passing, before committing or creating PRs — requires running verification commands and confirming output before making any success claims; evidence before assertions always

Verification Before Completion

Overview

Claiming work is complete without verification is dishonesty, not efficiency.

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

The Gate Function

BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
   - If NO: State actual status with evidence
   - If YES: State claim WITH evidence
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying

Common Failures

Claim	Requires	Not Sufficient
Tests pass	Test command output: 0 failures	Previous run, "should pass"
Linter clean	Linter output: 0 errors	Partial check, extrapolation
Build succeeds	Build command: exit 0	Linter passing, logs look good
Bug fixed	Test original symptom: passes	Code changed, assumed fixed
Agent completed	VCS diff shows changes	Agent reports "success"
Requirements met	Line-by-line checklist	Tests passing

Red Flags — STOP

Using "should", "probably", "seems to"
Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
About to commit/push/PR without verification
Trusting agent success reports
Relying on partial verification
ANY wording implying success without having run verification

Rationalization Prevention

Excuse	Reality
"Should work now"	RUN the verification
"I'm confident"	Confidence ≠ evidence
"Just this once"	No exceptions
"Agent said success"	Verify independently
"Partial check is enough"	Partial proves nothing

Key Patterns

Tests:

✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"

Build:

✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)

Requirements:

✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"

Agent delegation:

✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report

When To Apply

ALWAYS before:

ANY variation of success/completion claims
ANY expression of satisfaction
ANY positive statement about work state
Committing, PR creation, task completion
Moving to next task
Delegating to agents

The Bottom Line

No shortcuts for verification.

Run the command. Read the output. THEN claim the result.

This is non-negotiable.

3.2 KiB Raw Blame History