Install
$ agentstack add skill-franklywatson-claude-rig-verify-harness ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
verify-harness — Post-Install Verification
Run this skill after rig init to confirm everything is working.
Procedure
Run each check and report PASS/FAIL with evidence.
Session Start Hook
- [ ] S1: Session started without hook errors
- [ ] S2: Run
which rtk— report if available - [ ] S3: Run
which jcodemunch-mcp(orwhich uvx) — report if available - [ ] S4: Check if CWD is indexed: run
jcodemunch-mcp list-reposif available - [ ] S5: Check
.harness.yamlexists and parses
Tool Router (PreToolUse Hook)
- [ ] TR1: Run
grep -r test .in a test call — does the hook intercept it? - [ ] TR2: Run
find . -name '*.ts'— does the hook intercept it? - [ ] TR3: Run
sed -i 's/old/new/g' file— does the hook BLOCK it? - [ ] TR4: Run
git status— does the hook advise rtk (if available)? - [ ] TR5: Run
Readon a specific file — does it pass through? - [ ] TR6: Run
Greptool — does it advise jcodemunch (if indexed)? - [ ] TR7: Run
Globtool — does it advise jcodemunch (if indexed)? - [ ] TR8: Reference an external directory — does it trigger auto-index?
Enforcement (PostToolUse Hook)
- [ ] E1: Edit a source file — does it warn about missing test update?
- [ ] E2: Write a test with
jest.mock()— does constitutional check fire? - [ ] E3: Run a test that fails — does zero-defect check fire?
- [ ] E4: Edit source without test — does stale test warning appear?
- [ ] E5: During tdd+ phase, run full suite — does scope redirect fire?
- [ ] E6: During verify+ phase, run full suite — is it allowed?
Skills
- [ ] SK1:
/brain+shows in skill list - [ ] SK2:
/plan+shows in skill list - [ ] SK3:
/tdd+shows in skill list - [ ] SK4:
/verify+shows in skill list - [ ] SK5:
/review+shows in skill list - [ ] SK6:
/sdd+shows in skill list
Agents
- [ ] AG1: Scout agent definition exists
- [ ] AG2: Scout can be invoked with
Agent(subagent_type="scout") - [ ] AG3: code-reviewer agent definition exists
- [ ] AG4: code-reviewer can be invoked with
Agent(subagent_type="code-reviewer") - [ ] AG5: spec-reviewer agent definition exists
- [ ] AG6: spec-reviewer can be invoked with
Agent(subagent_type="spec-reviewer") - [ ] AG7: implementer agent definition exists
- [ ] AG8: implementer can be invoked with
Agent(subagent_type="implementer")
Configuration
- [ ] CF1: Change a rule in
.harness.yaml— does behavior change? - [ ] CF2: Default config was generated correctly
Report Format
Session Verification Report
============================
Session Start: X/5 passed
Tool Router: X/8 passed
Enforcement: X/6 passed
Skills: X/6 passed
Agents: X/8 passed
Configuration: X/2 passed
TOTAL: XX/35 passed
Failures:
- [ID]: [what happened]. Expected: [expected]. Got: [actual].
Remediation: [how to fix]
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: franklywatson
- Source: franklywatson/claude-rig
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.