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 site-map-retestgit 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/site-map-retest)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/site-map-retest"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/site-map-retest/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/site-map-retest"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/site-map-retest.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 | $0.00040 | $0.00625 |
| Opus 5 | $0.00020 | $0.00313 |
| Sonnet 5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
site-map-retest 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Drives the same deterministic verification the site-map workflow runs and reads what changed:
the engine re-resolves every cited file:line, re-derives the findings, and re-stamps the
stored map's earned trust tiers and its map-vs-code freshness. There is no separate retest
engine and no report replay — a re-run is the same run again, and drift shows up as stamped
proof in the map itself.
Use This When
Use this for the site-map-retest workflow: the user wants to know whether the map still
matches the code or prior gaps got fixed, not a fresh map.
Inputs
- The stored map at
docs/site-map/(the one source of truth). - Read
references/replay-rules.mdbefore narrating any change.
Procedure
The verification is the engine's; you drive it and narrate honestly.
- Run
paqad-ai sitemap run(or hit Run on the dashboard's Site map area); it verifies the stored map against the current code and stamps the earned trust and freshness back into it. - Read the drift:
anchors_broken > 0in the stamped freshness means cited code no longer resolves. Finding ids are content-addressed (SM-<hash8>), so a persisting finding keeps its id and the baseline ratchet marks itpre-existing; a finding that disappears was resolved by whatever change removed its evidence. - Narrate the split in the paqad voice — Safe to merge only when the run exits clean and no cited anchor is broken.
Output Contract
- A JSON object
{ findings: N, anchors_total: N, anchors_resolved: N, anchors_broken: N, new_since_baseline: N, pre_existing: N }. - The verdict is Safe to merge only when
findingsis 0 andanchors_brokenis 0.
Escalate / Stop Conditions
- Never invent a finding in a re-run; the engine's output is the only source.
- Never soften a finding: absence of proof is drift, not a fix — a surface whose cited evidence no longer resolves is a finding, never silently fine.
- Never hand-edit the stamped freshness; only the verb writes it.
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 · 65 lines · 40 tokens per session scan A 3933edfe4ed4
site-map-retest is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 625 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…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.