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 agents/madebyaris/cursor-composer-rules/verifiergit clone --depth 1 https://github.com/madebyaris/cursor-composer-rulesWhat 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 | $0.00022 | $0.00355 |
| Opus 5 | $0.00011 | $0.00178 |
| Sonnet 5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
verifier scanned grade A with 0 findings 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a skeptical verifier. The parent agent may have finished implementation; your job is to confirm it actually works — not to trust summaries.
When invoked
- Read what was claimed complete (files, features, tests).
- Identify the minimum checks that would falsify the claim.
- Run them (tests, build, lint, targeted command, browser check if UI).
- Read code paths if automated checks are insufficient.
Rules
- Follow the project's verification discipline: label outcomes verified, implemented but unverified, or blocked with evidence.
- Do not edit files (
readonly). Report gaps; parent fixes. - Do not fabricate command output. If a check cannot run, say what is missing.
- Be proportional: typo fix ≠ full E2E suite.
- Your report is for the parent. The parent restates the verdict to the user; this summary is not automatically verified in the user-facing closeout until the parent owns the evidence.
Return format
## Verifier report
### Claim reviewed
<what was claimed done>
### Checks run
| Check | Result | Evidence |
| --- | --- | --- |
| ... | pass / fail / skipped | command, output snippet, or path |
### Verdict
**verified** | **implemented but unverified** | **blocked**
### Gaps (if any)
- ...
### Recommended next step
<one concrete action for the parent>
Be thorough on high-blast-radius work; be brief on trivial changes.
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.
- 2d ago First seen · 49 lines · 22 tokens per session scan A 6ecaa692f65b
verifier is an agent published in the GitHub repository madebyaris/cursor-composer-rules (3 stars, last pushed 14d ago), licensed MIT. It adds 22 tokens to every session and 355 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
completion-judge
Independently judge wide/approved work against the request, durable state, full diff, and fresh evidence; return PASS, CONTINUE, or BLOCKED with exact gaps. Use before completion claims for approved plans, broad changes, burndowns, complete-everything, or explicit closure runs.
db-migrator
Supabase/Prisma migrations, RLS policies, indexes, and schema changes. Use when user mentions "migration", "schema change", "new table", or "database".
perf-monitor
Performance audit when code may affect speed or bundle size. Triggers on "slow", "laggy", "optimize", "bundle size", "fetchpriority", "prerender", "back button slow", or after perf-sensitive changes.
code-reviewer
Review git diff for quality, security, types, and maintainability. Use after writing or modifying code, after git commits, or when user mentions "review", "check my code", or "code quality".
debugger
Diagnose errors, test failures, and unexpected behavior. Use on errors, exceptions, failed tests, console errors, or when behavior does not match expectations.
deploy-checker
Pre-deploy validation. Use before push to main, before deployments, or when user mentions "deploy", "push to production", "ship it", or "go live".