Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/sumulige/sumulige-claude/verify-workgit clone --depth 1 https://github.com/sumulige/sumulige-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sumulige/sumulige-claude/verify-work)<a href="https://agentmods.dev/commands/sumulige/sumulige-claude/verify-work"><img src="https://agentmods.dev/badge/commands/sumulige/sumulige-claude/verify-work.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00006 | $0.00313 |
| Opus 5 | $0.00003 | $0.00156 |
| Sonnet 5 | $0.00001 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade B, and why
verify-work scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/verify/verify-log.md 2>/dev/null || echo "No verification log found" What it actually says
You are helping the user review and verify completed work.
Check Pending Tasks
First, read the verification log:
cat .claude/verify/verify-log.md 2>/dev/null || echo "No verification log found"
And check pending tasks:
cat .claude/verify/.pending-verify.json 2>/dev/null || echo "No pending tasks"
Verification Process
For each pending task, guide the user through:
- What was done - Summarize the action
- How to verify - Run appropriate verification commands:
- For code changes: run tests, linters
- For deployments: check staging environment
- For commits: verify CI/CD status
Common Verification Commands
# Run tests
npm test
# Check test coverage
npm run test:coverage
# Run linter
npm run lint
# Type check
npm run type-check
# Build verification
npm run build
# Check CI status (if using GitHub)
gh run list --limit 5
# Check PR status
gh pr status
Mark as Complete
After verification is successful, ask the user if they want to:
- Mark the task as verified (remove from pending)
- Keep it for later verification
- Add additional verification steps
To mark as complete, edit .claude/verify/.pending-verify.json to remove the completed task.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 64 lines · 6 tokens per session scan B 8582467c774d
verify-work is a command published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 313 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
doctor
Run read-only health checks on the Kobiton automate plugin (CLI, credentials, profile).
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
handoff
Force a session catchup or a memory promotion outside the hook lifecycle. Default is catchup (read-only); promote is HITL gated.
gate
You are the Gate System controller. Execute quality gate reviews based on the user's request.