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-critique-auditgit 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-critique-audit)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-critique-audit"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-critique-audit/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-critique-audit"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-critique-audit.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 | $0.00074 | $0.01482 |
| Opus 5 | $0.00037 | $0.00741 |
| Sonnet 5 | $0.00015 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
llm-wiki-critique-audit 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 12d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Critique Audit
Goal
Stress-test LLM-Wiki adoption before or during implementation using a criticism-first risk register.
When to use
Use when the user asks:
- "What are the arguments against LLM-Wiki?"
- "Where will this fail?"
- "Is this domain a bad fit?"
- "How do I avoid slop?"
- "Will this hurt my own understanding?"
- "Is this just RAG?"
- "Will token costs explode?"
- "Can this work for a team?"
- "What are the residual risks after mitigations?"
Inputs
- A description of the audit target: a domain (research papers, trading notes, personal notes), an existing vault/docs folder, a proposed team rollout, an implementation (CLI, plugin, MCP/API server), or an operating loop (capture, triage, ingest, lint, refresh, publish).
- Any existing vault schema,
CLAUDE.mdcontracts, or domain wiki structure for the target, so the domain fit screen and risk scorecard are grounded in real answers rather than assumptions. - Scale and cost context: source count, corpus size, planned team size, and current token/time budget, needed to answer the domain fit screen and score the token-burn and scale-ceiling risk classes.
- Any mitigations or rollout plans already committed to, so Step 4 can separate genuine mitigations from residual risk instead of re-deriving them from scratch.
- The reference docs listed below when present in the repo; re-verify the risk scorecard against their current content rather than relying on memorized summaries.
Required references
Read these when available:
references/docs/criticism-and-mitigations.mdskills/llm-wiki-faq/references/criticism-pack.mdreferences/docs/04-anti-slop-and-trust.mdreferences/docs/08-evaluation-and-metrics.mdreferences/docs/security/skill-supply-chain.mdreferences/docs/20-ingestion-pipelines.md
Procedure
1. Identify the target
Classify the audit target:
| Target | Examples |
|---|---|
| domain | research papers, market research, repo docs, trading, personal notes |
| existing vault | Obsidian vault, docs folder, repo wiki |
| proposed rollout | team/company adoption, Confluence replacement, PR workflow |
| implementation | CLI, plugin, MCP/API server, retrieval stack |
| operating loop | capture, triage, ingest, lint, refresh, publish |
What ships with it
6 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.
- references/docs/04-anti-slop-and-trust.md 4.9 KB
- references/docs/08-evaluation-and-metrics.md 3.8 KB
- references/docs/20-ingestion-pipelines.md 18 KB
- references/docs/criticism-and-mitigations.md 18 KB
- references/docs/security/skill-supply-chain.md 2.2 KB
- references/templates/source-manifest.yaml 2.2 KB
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.
- 12d ago First seen · 185 lines · 74 tokens per session scan A 64d4b88291e8
llm-wiki-critique-audit is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 74 tokens to every session and 1,482 once invoked, about $0.0004 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-boundary
Rank the "frontier" pages of a wiki — the crossroads many pages link to that stay thin inside — so you can decide where research would pay off most. Use when the user says "what should I write about next", "where are the gaps", "which pages need work", "find the thin hub pages", "boundary pages", "/wiki-boundary"…