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 po4yka/llm-wiki-skills --skill llm-wiki-github-actiongit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote 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/po4yka/llm-wiki-skills/llm-wiki-github-action)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-github-action"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-github-action/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/po4yka/llm-wiki-skills/llm-wiki-github-action"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-github-action.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 | $0.00053 | $0.01011 |
| Opus 5 | $0.00026 | $0.00505 |
| Sonnet 5 | $0.00011 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
llm-wiki-github-action 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki GitHub Action
Goal
Create safe GitHub Actions workflows for LLM-Wiki validation and maintenance.
When to use
- The user wants a scheduled
wiki-lintor wiki-health report published as a workflow artifact. - The user wants PR-based automation for generated docs or maintenance changes and wants to avoid direct pushes to
main. - The user needs Agent Skills frontmatter validation (or other repo-specific validation scripts) wired into CI.
- The user wants to add or enable one of the starter evals, ingestion, publish, or security workflows.
- The user is deciding what GitHub Actions permissions or triggers a wiki-maintenance job should have.
Starter templates
Use these local templates when available in a full repository checkout. In a single-skill install, recreate the same workflow shapes from this list:
llm-wiki-evals.github-actions.ymlfor retrieval, grounding, promptfoo and wiki-health checks.llm-wiki-ingestion.github-actions.ymlfor source manifests, ingestion fidelity, parser security and retrieval smoke checks.llm-wiki-publish.github-actions.ymlfor export profile validation, redaction/security checks, artifacts and optional Pages publish.llm-wiki-security.github-actions.ymlfor secrets, dependency, OSV, Semgrep, red-team and export-policy checks.
The starter workflow schedules are commented out by default. Enable cron only after workflow_dispatch has run successfully and the repository owner accepts the recurring cost and external calls.
Inputs
- Repository path.
- Desired automation: validation, lint, scheduled report, maintenance PR, skill validation.
- Permission constraints.
- Whether Actions should write files, open PRs, or only upload reports.
Procedure
1. Choose automation mode
| Mode | Use when |
|---|---|
| report-only | Early adoption or sensitive repos. |
| artifact report | Reports should not change the repo. |
| PR-based update | Generated output needs human review. |
| validation | Validate schemas, links, skills and frontmatter. |
What ships with it
4 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.
- 10d ago First seen · 128 lines · 53 tokens per session scan A 8a03b65b51ad
llm-wiki-github-action is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 17d ago), licensed MIT. It adds 53 tokens to every session and 1,011 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 2026-08-31.
Other skills, from other repositories
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
okf-harness
One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…