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 map-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/map-verification)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/map-verification"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/map-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/map-verification"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/map-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 | $0.00042 | $0.00587 |
| Opus 5 | $0.00021 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
map-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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Provides the Tier-B judgment layer: the engine's deterministic checks settle what they can and hand over a table of claims they could not — an evidence pointer that half-resolves, a transition whose runtime behaviour is ambiguous. This skill refutes or confirms each, grounded in the code, so an inconclusive claim becomes either a finding or a fact — never a shrug.
Use This When
Use this after assembly, over the engine's inconclusive-claim table. It settles only what the deterministic checks left open; it never re-litigates a claim the engine already proved.
Inputs
- The machine-built claim digest from the run bundle (each claim with its evidence and why it is inconclusive).
- The code the claims cite.
- Read
references/refutation-discipline.mdbefore recording a verdict.
Procedure
The deterministic checks are the engine's; you settle only the inconclusive residue.
- Read each inconclusive claim and open the evidence it cites.
- Try to refute it first: does the code actually show what the claim asserts? Default to
inconclusivewhen the evidence does not settle it, never toconfirmed. - Record a verdict (
confirmed | refuted | inconclusive) with the resolvingfile:line, and letsite-map-gap-analysisturn confirmed problems into findings.
Output Contract
- A JSON object
{ verdicts: [{ claim_id, verdict, evidence, rationale }] }. verdict∈confirmed | refuted | inconclusive.- Every
confirmedorrefutedverdict carries a resolvingfile:line; aninconclusiveone states what evidence is missing.
Escalate / Stop Conditions
- Default to
inconclusivewhen the evidence does not settle the claim. Do not confirm to look thorough or refute to look clean. - Do not invent a new claim here; new problems are a fresh
site-maprun, not a verification verdict. - A claim whose evidence no longer resolves is
confirmeddrift, never quietly dropped.
Resources
references/refutation-discipline.mdagents/openai.yaml
What ships with it
2 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.
- 8d ago First seen · 66 lines · 42 tokens per session scan A c05f29234e4f
map-verification is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 587 once invoked, about $0.0002 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
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
auto-review
A code-review skill that examines changed code using the TRUST 5 criteria and automated checks. It can review files, commit ranges, or changes assigned a risk level, with optional review strategies and providers.
ax-annotation
@AX code annotation workflow skill for agent-driven tag application.
ddd
A development method for improving existing code while preserving its current behavior. It follows an analyze, preserve, and improve cycle, using tests and small changes to reduce unintended effects.
review
A structured checklist for reviewing software code. It covers tests, readability, consistency, security, and whether changes can be tracked.
refactoring
A set of techniques for improving code structure while keeping its existing behavior unchanged. Refactoring means reorganizing code without intentionally changing what it does.