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-gap-analysisgit 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-gap-analysis)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/site-map-gap-analysis"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/site-map-gap-analysis/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-gap-analysis"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/site-map-gap-analysis.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 | $0.00590 |
| Opus 5 | $0.00021 | $0.00295 |
| Sonnet 5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
site-map-gap-analysis 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
Converts the engine's graph invariants (orphans, dead ends, guard-less backstage surfaces,
broken cross-references) and the verifier's confirmed verdicts into SM-* findings, then
composes the gap report. Every finding is content-addressed, evidenced, and carries a concrete
fix — nothing here is a vague observation.
Use This When
Use this after verification, once invariants and verdicts exist. It produces the findings the receipt and the retest depend on.
Inputs
- The engine's graph invariants and the finding index in the run bundle.
- The verifier's confirmed verdicts from
map-verification. - Read
references/finding-composition.mdbefore writing a finding.
Procedure
The findings come from the engine's invariants and the confirmed verdicts — never from your own fresh reading of the code.
- Read the engine's invariants and finding index; each already carries a category and evidence.
- Fold in the confirmed Tier-B verdicts, dedup against the existing findings, and reuse
finding-normalizerso ids and severities follow the shared vocabulary. - Compose the gap report: findings ordered by severity, each with its
SM-<hash8>id, category, evidence, and a concrete fix.
Output Contract
- A JSON object
{ findings: [{ id, category, severity, evidence, suggestion, affected_files }], summary }. - Every finding id is a content-addressed
SM-<hash8>; the category is a field (SM-ADD | SM-REMOVE | SM-EDGE-STALE | SM-GUARD-DRIFT | SM-ORPHAN | SM-DEADEND | …). - Every finding carries resolving evidence and a concrete
suggestion.
Escalate / Stop Conditions
- Never restate a finding the engine or a confirmed verdict did not produce. Absence of a finding is not a finding.
- Never expose a secret's bytes in evidence — cite
file:line, rule, and fingerprint only. - A finding with no concrete fix is incomplete; state the exact remediation or do not ship it.
Resources
references/finding-composition.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 · 65 lines · 42 tokens per session scan A 8e303dbb0469
site-map-gap-analysis 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 590 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
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-fix
A bug-fixing workflow that first reproduces a problem with a test, then applies the smallest code change needed. It also checks the related code path and runs tests afterward.
environment-diagnostics
Environment variable validation and configuration verification. Checks that required variables are set, config files parse correctly, ports are available, and system dependencies meet version requirements.
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.
ast-refactoring
A code-refactoring guide that uses an abstract syntax tree, a structured representation of source code, to make changes based on code meaning rather than text matching.
entropy-scan
A codebase health scan that measures disorder and highlights technical debt, meaning code problems that make future changes slower or riskier. It checks complexity, dependencies, repeated code, file size, and recent change frequency.