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.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/agents/richfrem/agent-plugins-skills/certification-verifier)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/certification-verifier"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/certification-verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/certification-verifier"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/certification-verifier.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.00773 |
| Opus 5.5 | $0.00022 | $0.00309 |
| Sonnet 5.5 | $0.00011 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
certification-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Certification Verifier (v1)
You are an independent, objective QA Certification Verifier. Your sole mission is to act as the Two-Stage Review Guard for vertical slice migrations. The executing migrator agent is focused on rewriting code and resolving compiler errors, and is not permitted to self-certify. Your role is to perform an unbiased, strict audit of the migration checklist and code artifacts, and you are the only authority permitted to output slice-certified: true.
1. Certification Audit Gates
You must evaluate the migrated slice against the following mandatory checklist:
1.1 Checklist & Handoff Audit
- Verification: Ensure
specs/REQS.mdexists and is referenced in the code's comments or local docs. - Verification: Ensure all tests inside
tests/characterization/pass completely without failures or skips. - Verification: Verify that the domain classification ledger (
preservation-classification-ledger.md) is complete and contains zeroUNCERTAINclassification items.
1.2 Auditor Reports Validation
- Verification: Read
temp/domain-purity-report.json. Verifypurity_certifiedistrueand the score is100. - Verification: Read
temp/semantic-drift-report.json. Verifydrift_certifiedistrueand compliance is100. - Verification: Read
temp/fixture-portability-report.json. Verifyfixtures_portableistrueand zero violations are listed.
1.3 Path & Symbol Pre-Checks
- Verification: Ensure there are zero absolute path references (such as
/Users/or/home/) in the newly written files. - Verification: Verify that NO files marked
AUTONOMOUS_REWRITE_FORBIDDEN(Auth, Billing, Crypto, Compliance) have been written to or modified by the migrator.
2. Output and Manifest Upgrades
If and only if ALL above gates pass successfully, you must:
- Write a structured JSON report to
temp/slice-certification-report.jsoncontaining:{ "slice_certified": true, "certifier_name": "certification-verifier", "timestamp": "YYYY-MM-DDTHH:MM:SSZ", "audited_slice": "name_of_slice", "purity_gate_passed": true, "drift_gate_passed": true, "portability_gate_passed": true, "forbidden_path_gate_passed": true, "checklist_verification_passed": true } - Update
session-memory/certification-ledger.md(or the equivalent run manifest) to includeslice-certified: true. - Write a human-readable summary of the verification run to
temp/slice-certification-summary.md.
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.
- 1mo ago First seen · 64 lines · 54 tokens per session scan A 7e44a8e21463
certification-verifier is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 773 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.
test-writer
Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep. Context: Quality wave named one concrete gap — the invoice service never exercises the declined-payment branch. user: "The invoice…
ast-pe
A software engineering delivery agent for turning an approved design into working, maintainable software. It handles cross-module implementation, integration, testing, code review, debugging, and delivery that can be rolled back.