Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AIwork4me/open-llm-wikinpx agentmods add skills/aiwork4me/open-llm-wiki/wiki-lintWrote 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/aiwork4me/open-llm-wiki/wiki-lint)<a href="https://agentmods.dev/skills/aiwork4me/open-llm-wiki/wiki-lint"><img src="https://agentmods.dev/badge/skills/aiwork4me/open-llm-wiki/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/aiwork4me/open-llm-wiki/wiki-lint"><img src="https://agentmods.dev/badge/skills/aiwork4me/open-llm-wiki/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 | $0.00084 | $0.01123 |
| Opus 5 | $0.00042 | $0.00562 |
| Sonnet 5 | $0.00017 | $0.00225 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
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 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Lint
Audit an open-llm-wiki vault for structural, traceability, and maintenance problems. Default to report-only.
Runtime Tool
Use the deterministic linter whenever available. For semantic-growth audits, also use claim/QA scripts when available:
uv run python scripts/wiki_lint.py "<vault>" --fail-on p1
uv run python scripts/wiki_discover_sources.py "<vault>"
uv run python scripts/wiki_claims.py "<vault>"
uv run python scripts/wiki_normalize_metrics.py "<vault>" --in-place
uv run python scripts/wiki_semantic_qa.py "<vault>" --write-report --fail-on p1
uv run python scripts/wiki_contradictions.py "<vault>" --write-report
uv run python scripts/wiki_science_review.py "<vault>" --queue --write-report
The script checks structure, frontmatter, QA gates, contradiction reports, links, index coverage, stale claims, claim graph availability, and log format. Read reports before doing any manual inspection.
Safety Boundary
- Read-only by default.
- Fix mode requires explicit user approval or an automation prompt that clearly authorizes maintenance writes.
- Never edit files in
raw/. - Never rewrite QA reports; they are append-only audit records.
- Do not rewrite
claims/claims.jsonlunless the user asked for semantic refresh or maintenance fix mode. - Queue files under
_state/are state, not evidence. They may be updated by explicit maintenance or scheduled growth runs. - When fixing, show a write plan first and keep edits targeted.
Checks
1. Structure
- required directories exist:
raw/,sources/,concepts/,drafts/,qa-reports/,claims/,_state/,templates/ - required root files exist:
SCHEMA.md,index.md,log.md - source page filenames match
LLM-NNNN.md
2. Frontmatter
- source pages include
id,title,status,created,updated,source, andtags - stable source pages live in
sources/ - draft source pages live in
drafts/ - concept pages include
id,title,created, andupdated - IDs are unique and sequential enough to audit
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 · 130 lines · 84 tokens per session scan A b317094d46ba
wiki-lint is a skill published in the GitHub repository AIwork4me/open-llm-wiki (2 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,123 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
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-health
Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…