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-maintainergit 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-maintainer)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/site-map-maintainer"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/site-map-maintainer/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-maintainer"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/site-map-maintainer.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 | $0.00568 |
| Opus 5 | $0.00021 | $0.00284 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
site-map-maintainer 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
Watches a feature-development change for edits that would drift the site map — a new route, a changed guard, a removed screen — and patches only the affected surfaces. It is the reason a change that touches navigation cannot reach "Safe to merge" with a stale map: the freshness gate flags the drift, and this skill resolves it with a scoped patch, not a full re-map.
Use This When
Use this inside a feature-development change, once the diff is known, when a changed file is one the map cites or a flow-relevant path (routes, command programs, endpoint handlers, guards). Skip it when the change touches nothing the map depends on.
Inputs
- The change's
changed_files. - The stored
docs/site-map/app-map.yamland its stamped freshness (the broken-anchor count the freshness gate reads). - Read
references/patch-scope.mdbefore patching.
Procedure
The drift detection is the engine's (the stamped freshness records which cited anchors no longer resolve); your job is the scoped patch.
- Run
paqad-ai sitemap run; read which cited anchors broke and which surfaces the changed files cite. - Patch only those surfaces — add the new one, update the changed guard, mark the removed one — leaving untouched surfaces exactly as curated.
- Re-run the verb to confirm the freshness gate is satisfied and the map validates.
Output Contract
- A JSON object
{ patched_surfaces: [...], anchors_repaired: [...], still_broken: [...] }. - Every patched surface carries resolving evidence from the changed files.
still_brokenis empty when the change is complete; a non-empty list is a blocking gap.
Escalate / Stop Conditions
- Do not re-map the whole app for a scoped change; patch only what the diff drifted.
- Do not overwrite a curated surface that the change did not touch.
- Stop and surface the drift when a change removes a surface that journeys still reference — that is a decision, not a silent deletion.
Resources
references/patch-scope.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 d831dcd2cfc3
site-map-maintainer 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 568 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
prd
A guide for writing a PRD, or Product Requirements Document, which explains what a product or feature should achieve and who it is for. It covers goals, users, success measures, limits, prior work, and excluded scope.
product-discovery
Product discovery workflow with OST, assumption testing, and interview scripts.
planning
A guide for planning software features and turning requests into clear requirements. It uses EARS, a plain format for stating what a system must do under specific conditions.
auto-status
A project dashboard skill that reports the current specification status for a project and its submodules. A specification is a written description of what should be built and how it should behave.
squads-cli
Squads CLI — operate your AI workforce through the loop; intent in, reviewed work out. TRIGGER when running squads, dispatching agents, triaging the inbox, reading/writing memory, recording feedback, or checking status/usage.
gh
You have access to gh (GitHub CLI) for repository and project management.