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 skills add Eliyce/paqad-ai --skill retest-verificationgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/skills/eliyce/paqad-ai/retest-verification)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/retest-verification"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/retest-verification/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/skills/eliyce/paqad-ai/retest-verification"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/retest-verification.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 | $0.00017 | $0.00541 |
| Opus 5 | $0.00009 | $0.00270 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
retest-verification 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 9d 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
What It Does
Replays prior pentest findings against fresh project evidence so retest reports can classify each finding as fixed, still open, or requiring manual verification.
Use This When
Use this only for the pentest-retest workflow when a prior pentest report has already identified findings to verify.
Inputs
- Read the source pentest sidecar first.
- Read
references/retest-status-rules.mdbefore assigning statuses. - Read fresh evidence gathered during the current retest run.
Procedure
- Run
scripts/load-source-findings.sh <sidecar.json>— validates the schema and emits one JSON row per finding to iterate over. - For each id, gather fresh code/docs/advisory/runtime evidence and pick a status from
assets/status-vocabulary.txt(fixed | still-open | needs-manual-verification). - New gaps (not in the source report) belong in a separate report; never silently merge them here.
- Format per
assets/output.template.md; validate withscripts/lint-output.sh <retest.md> <sidecar.json>— fails if any id is invented.
Output Contract
- Match
assets/output.template.md:## Retest Decisionswith### {{id}} → {{status}}per finding plus Original title, Severity, Fresh evidence, Reasoning. - Status must be
fixed | still-open | needs-manual-verification. - Output must pass
scripts/lint-output.sh(exit 0).
Escalate / Stop Conditions
- Ask when the source report sidecar is missing fields required to replay a finding.
- Warn when fresh evidence is blocked and the finding depends on runtime validation.
- Do not invent a fixed status when the current evidence is merely absent.
Resources
references/retest-status-rules.mdscripts/load-source-findings.shscripts/lint-output.shassets/output.template.mdassets/status-vocabulary.txtagents/openai.yaml
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 64 lines · 17 tokens per session scan A dfaa667845d1
retest-verification is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 541 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 2026-09-03.
Other skills, from other repositories
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
testing-strategy
A testing guide that explains how to combine unit, integration, contract, and end-to-end tests. End-to-end tests check complete user flows, while integration tests check components working together.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.