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 TrueHOOHA/LLM-Wiki --skill llm-wiki-lintgit clone --depth 1 https://github.com/TrueHOOHA/LLM-WikiWrote 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/truehooha/llm-wiki/llm-wiki-lint)<a href="https://agentmods.dev/skills/truehooha/llm-wiki/llm-wiki-lint"><img src="https://agentmods.dev/badge/skills/truehooha/llm-wiki/llm-wiki-lint/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/truehooha/llm-wiki/llm-wiki-lint"><img src="https://agentmods.dev/badge/skills/truehooha/llm-wiki/llm-wiki-lint.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 | $0.00067 | $0.02227 |
| Opus 5 | $0.00034 | $0.01113 |
| Sonnet 5 | $0.00013 | $0.00445 |
| Haiku 4.5 | $0.00007 | $0.00223 |
Grade A, and why
llm-wiki-lint 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 11d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki Lint Skill
Purpose
Run a structural and logical health check of the wiki against OKF (SPEC.md) and the producer conventions in AGENTS.md, then coordinate and apply agreed fixes.
When to Use
Use this skill when the operator asks to health-check the wiki, or periodically (e.g., after every 10 ingests or when the wiki feels unwieldy).
Inputs
- Optional: specific area to focus on (e.g., "check for contradictions in the AI section").
Single Source of Truth
The page schema (frontmatter fields and recommended sections per type, cross-link and citation rules, index/log formats) is defined only in AGENTS.md and OKF (SPEC.md). When validating, read AGENTS.md § Frontmatter Contract, § Page Types & Conventions, § Cross-linking, § Citations, and § Update Rules for Special Files, plus SPEC.md §4–§9 — never hardcode or re-derive the schema here.
Scope
The bundle root is wiki/. Validate every .md under wiki/entities/, wiki/concepts/, wiki/sources/, and wiki/syntheses/ (skip wiki/templates/). Also validate the reserved files wiki/index.md and wiki/log.md. Files outside wiki/ are not part of the bundle and are not checked.
Checks
1. OKF Conformance (structural, SPEC.md §9)
For every concept document under wiki/ (excluding index.md, log.md, templates/):
- Frontmatter present and parseable: a
----delimited YAML block exists at the top (high if missing/malformed). typenon-empty: thetypefield is present and non-empty (high if missing).- No legacy fields:
updatedandsource_pathare not used (they migrated totimestampandresource) (medium). - Recommended fields present:
title,description,tags,timestamp(low if absent — these are OKF-recommended, not strictly required). - Source pages:
resourceis present, begins withraw/sources/orraw/assets/, AND the file at that path exists on disk (high if missing/malformed; high if the referenced file does not exist).
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.
- 11d ago First seen · 129 lines · 67 tokens per session scan A cdeccaa4d054
llm-wiki-lint is a skill published in the GitHub repository TrueHOOHA/LLM-Wiki (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,227 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
impl-validator
Validate whether an implementation matches its stated goal. Use this skill when a skill or agent wants a second opinion on its own output, when the user says "check this implementation", "validate what you did", "is this correct?", "review the output", or "did you do this right?". Also spawned automatically as a…
agentsop-domain-eval-set
Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-harness) which measure GENERAL capability. Only a held-out domain set predicts whether THIS system works on YOUR data. Collect real examples, label…
agentsop-regression-gate
Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change — gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill.
agentsop-test-fix-loop
Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test → reads the output → fixes → re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion (exit code, type-checker output, failing…
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
test-roadmap
EXPERIMENTAL. Analyzes a repository and any existing test suite, grades existing tests for weakness, classifies mocks, emits a phased roadmap for building a test suite that catches real regressions, then executes those phases one at a time. Use when planning or building a test suite, assessing whether existing tests…