MUST invoke before claiming work is complete, fixed, or passing.
Forces you to run fresh verification commands before any completion claims. Triggers whenever you're about to say work is done, passing, or fixed.
/plugin marketplace add astrosteveo/harness/plugin install astrosteveo-harness@astrosteveo/harnessThis skill inherits all available tools. When active, it can use any tool Claude has access to.
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.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
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
| 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 |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
Tests:
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
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
From 24 failure memories:
ALWAYS before:
Rule applies to:
What to preserve: Test output, build logs, command output, screenshots of UI states.
Where to save:
.harness/ docs - detailed logs for complex verificationsRetention: Keep until PR merged, minimum. Complex changes: keep longer.
Why: Supports "evidence over claims" - reviewers can verify your verification.
Immediate actions:
Rollback options:
git reset --soft HEAD~1 - undo commit, keep changes stagedgit revert <sha> - create reverting commit (safe for pushed code)Rollback vs fix forward:
Post-failure checklist:
After verification passes, present completion options:
Implementation complete. What would you like to do?
1. Merge back to <base-branch> locally
2. Push and create a Pull Request
3. Keep the branch as-is (I'll handle it later)
4. Discard this work
Which option?
Option 1: Merge Locally
git checkout <base-branch>
git pull
git merge <feature-branch>
<run tests again> # verify merged result
git branch -d <feature-branch>
Option 2: Push and Create PR
git push -u origin <feature-branch>
gh pr create --title "<title>" --body "## Summary
<bullets>
## Test Plan
- [ ] <verification steps>"
Option 3: Keep As-Is Report: "Keeping branch <name>."
Option 4: Discard Require typed confirmation: "Type 'discard' to confirm."
git checkout <base-branch>
git branch -D <feature-branch>
| Option | Merge | Push | Keep Branch |
|---|---|---|---|
| 1. Merge locally | ✓ | - | Delete |
| 2. Create PR | - | ✓ | Keep |
| 3. Keep as-is | - | - | Keep |
| 4. Discard | - | - | Force delete |
No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.