Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add lookatitude/guild/plugin install guildWrote 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/lookatitude/guild/wiki-lint)<a href="https://agentmods.dev/skills/lookatitude/guild/wiki-lint"><img src="https://agentmods.dev/badge/skills/lookatitude/guild/wiki-lint.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 | $0.00000 | $0.01649 |
| Opus 5 | $0.00000 | $0.00825 |
| Sonnet 5 | $0.00000 | $0.00330 |
| Haiku 4.5 | $0.00000 | $0.00165 |
Grade A, and why
guild-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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guild:wiki-lint
Implements the knowledge layer audit contract: wiki structure + required frontmatter, decision ADR-lite shape, contradiction policy ("newer wins unless older has confidence: high"), and the lint-after-write discipline (runs after guild:wiki-ingest and guild:decisions write). Cadence: weekly + batch threshold + explicit invocation. Health report only; never auto-edits.
Read-only auditor. Complements guild:wiki-ingest (write) and guild:wiki-query (read) by checking both contracts hold across the whole wiki tree. Finds structural drift; never repairs it.
Input
- wiki root —
.guild/wiki/walked recursively. Every.mdis a candidate page EXCEPTindex.md(catalog),log.md(append-only log), andlint-*.md(prior reports). - raw root —
.guild/raw/sources/walked forsource_refsresolution; each<slug>/must containoriginal.*+metadata.jsonperguild:wiki-ingest. - now — current UTC timestamp, for
expires_atcomparison and the report filename.
Lint takes no user arguments; it walks the entire wiki on every invocation.
Step 0 — the deterministic core (always run first)
Run the mechanical checks via the script — never reproduce them by hand:
npx tsx ${GUILD_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$HOME/.local/share/guild/dist/claude-code}}/scripts/wiki-lint-checks.ts --root <repo-root>
It owns check #9 (pending-grade-review — migration-drafted importance_draft: true grades awaiting operator review; cleared by migrate-guild.ts --accept-grades) and the missing-importance: check, exits 0/2, and its
findings are folded verbatim into the report below. The semantic checks
(contradictions, stale claims, ADR shape) remain this skill's own work.
Checks performed
Run all nine checks every invocation. Each finding carries a severity: blocking (a hard contract is broken — ingest or decisions skill violated), important (contradicts plan guidance, needs human attention), or nit (small hygiene issue).
What ships with it
2 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.
- 7d ago First seen · 82 lines · 0 tokens per session scan A 225a4bf735a2
guild-wiki-lint is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,649 tokens. 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…