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 chipi/agentic-ai-homelab --skill docs-preflightgit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/docs-preflight)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/docs-preflight"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/docs-preflight.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 5.1 | $0.00097 | $0.00739 |
| Opus 5 | $0.00048 | $0.00369 |
| Sonnet 5 | $0.00019 | $0.00148 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
docs-preflight 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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-preflight
Run the project's strict docs build locally and report green/red before a docs commit lands. Strict mode is what CI runs — catching a broken cross- reference here costs ~20s; catching it in CI costs a wasted push and a red badge.
When this applies
The change touches any docs-affecting path: docs/**, mkdocs.yml,
requirements-docs.txt, a Makefile docs target, conf.py,
docusaurus.config.*, book.toml. If in doubt and a docs toolchain exists, run
it — it's cheap.
Detect the toolchain, then run its strict build
Use the first match, top to bottom. A repo's own make target is preferred
because it already encodes the venv and the correct strict flags.
- Makefile docs target —
grep -E '^docs-build:|^docs:' Makefile. If present, runmake docs-build(ormake docs). This is the common case for repos scaffolded from the operator'snew-projecttemplate. - MkDocs —
mkdocs.ymlat repo root. Prefer the project venv:.venv/bin/mkdocs build --strict --cleanif.venv/bin/mkdocsexists- else
python -m mkdocs build --strict --clean
- Sphinx —
docs/conf.py.sphinx-build -W -b html docs /tmp/_docs_preflight(-Wpromotes warnings to errors = strict). - Docusaurus / npm —
package.jsonwith a docs build script (docs:build,build:docs, or adocsworkspace). Run that script; Docusaurus fails on broken links by default. - mdBook —
book.toml.mdbook build.
If none match, say so — there is nothing to preflight. Do not invent a build.
Report
- Run in the foreground and show full output (do not
| tail), so streaming warnings are visible. - End with one unambiguous line:
DOCS PREFLIGHT: PASSorDOCS PREFLIGHT: FAIL. - On FAIL, surface the specific offenders — unresolved links, pages missing from nav, orphan warnings — not just the exit code.
Conventions this enforces
- Green local, then commit. Never push-and-pray on the docs build; reproduce and fix locally first.
- No new deps to make a build pass. Use the project's existing toolchain and venv. If a dependency is genuinely missing, report it — do not install silently.
- When linking from inside a docs tree to a file outside it, strict builders
can't resolve relative paths — use absolute repo URLs
(
https://github.com/<org>/<repo>/blob/main/...).
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.
- 7d ago First seen · 56 lines · 97 tokens per session scan A 39045186a733
docs-preflight is a skill published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 739 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.