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 agentmods add skills/caipe-io/ai-platform-engineering/update-docsnpx skills add caipe-io/ai-platform-engineering --skill update-docsgit clone --depth 1 https://github.com/caipe-io/ai-platform-engineeringWrote 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/caipe-io/ai-platform-engineering/update-docs)<a href="https://agentmods.dev/skills/caipe-io/ai-platform-engineering/update-docs"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/update-docs.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.02321 |
| Opus 5 | $0.00035 | $0.01161 |
| Sonnet 5 | $0.00014 | $0.00464 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
update-docs 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 5d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-docs
Audit every documentation surface in ai-platform-engineering and fix what is out of date.
What this skill checks
| # | Surface | Stale when… |
|---|---|---|
| 1 | Release blog posts | A git tag exists with no matching docs/releases/ file |
| 2 | Homepage version string | Helm --version in docs/src/pages/index.tsx doesn't match latest git tag |
| 3 | Docusaurus version config | lastVersion in docusaurus.config.ts doesn't match latest git tag |
| 4 | Docusaurus version snapshot | A tag exists but no versioned_docs/version-X.Y.Z/ snapshot |
| 5 | Features page | docs/src/pages/features.tsx tiles don't reflect new feature docs in docs/docs/features/ |
| 6 | Agent docs | A directory under ai_platform_engineering/agents/ has no matching docs/docs/agents/<name>.md |
| 7 | Sidebar completeness | A directory under docs/docs/ is not referenced in docs/sidebars.ts |
| 8 | Navbar version label | The 0.4.X (Latest) label in the navbar version dropdown is behind the latest tag |
Execution context
Runs in two modes:
- Coding agent (Claude Code) — runs
git,find,grepdirectly and writes fixes to disk. - Chat-only — renders a checklist of findings; states which files to edit and what to change.
Step 1 — Collect ground truth
Run all of the following in parallel.
# Latest stable git tag
LATEST=$(git tag --sort=-version:refname | grep -E '^[0-9]+\.[0-9]+\.[0-9]+$' | head -1)
echo "Latest tag: $LATEST"
# All release tags
git tag --sort=-version:refname | grep -E '^[0-9]+\.[0-9]+\.[0-9]+$'
# Existing release blog posts (extract version from filename)
ls docs/releases/*.md 2>/dev/null | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | tr '-' '.'
# Current lastVersion in docusaurus config
grep 'lastVersion' docs/docusaurus.config.ts
# Current Helm version string on homepage
grep -o "'--version [0-9.]*'" docs/src/pages/index.tsx ||
grep -o '"--version [0-9.]*"' docs/src/pages/index.tsx ||
grep 'version' docs/src/pages/index.tsx | grep helm | head -3
# Versioned snapshots
ls docs/versioned_docs/
# Agent implementation directories
ls ai_platform_engineering/agents/
# Agent doc files
ls docs/docs/agents/*.md 2>/dev/null | xargs -I{} basename {} .md
# Feature doc files
ls docs/docs/features/*.md 2>/dev/null | xargs -I{} basename {} .md
# Top-level docs directories
ls -d docs/docs/*/
# Sidebar entries
grep -E "^\s+'[a-z]" docs/sidebars.ts | head -40
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.
- 5d ago First seen · 245 lines · 70 tokens per session scan A 2428397ed5ba
update-docs is a skill published in the GitHub repository caipe-io/ai-platform-engineering (405 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 2,321 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
openhermit-admin
Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.
skill-creator
Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.
openhermit-guide
Explain how an OpenHermit agent behaves for the people interacting with it — owners, users, and guests. Covers roles, identity linking, the agent's tools, access levels, channels, the policy model, and the approval flow. Use when someone asks how an OpenHermit agent works from a caller's perspective. For deploying or…
focus
Single-task execution loop with structured context handoff. Enforces the discipline of plan → execute → simplify → review → close. Uses Beads (bd) for task tracking so context survives across sessions without artifact clutter. A new session runs bd ready and picks up exactly where the last one left off. Supports…
compose
Workflow Pipeline Builder. A meta-workflow that takes a goal and designs which existing workflow skills to chain together, in what order, with what parameters. Spawns agents to independently propose different workflow compositions for the same goal. The only workflow that operates on the WORKFLOW LAYER rather than the…
constraint-inversion
Constraint Inversion — What-If Removal. Takes a design with stated constraints and spawns N agents, each removing or inverting ONE constraint to explore what becomes possible without it, then synthesizes findings into a constraint dependency map that reveals which constraints are truly load-bearing vs merely assumed.