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 agentmods add commands/teammanagementplugin/claude-plugin/wiki-lintgit clone --depth 1 https://github.com/TeamManagementPlugin/claude-pluginWhat 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 | $0.00014 | $0.00736 |
| Opus 5 | $0.00007 | $0.00368 |
| Sonnet 5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00074 |
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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Lint
Audit wiki/pages/ for structural and content quality issues.
Scale Check
First, count the number of .md files in wiki/pages/:
find wiki/pages -name "*.md" | wc -l
If more than 50 pages: Delegate this entire lint operation to the Agent tool (subagent_type: "general-purpose") with the prompt below. This prevents context overflow from reading all pages inline.
If 50 or fewer pages: Perform the lint inline.
Checks
Pages may be nested in category subdirectories (wiki/pages/<category>/<slug>.md) or flat (wiki/pages/<slug>.md, legacy). find wiki/pages -name "*.md" already recurses. Normalize every page and link target to its wiki-root-relative path (e.g. pages/<category>/<slug>.md) before comparing — links are written relative to the wiki root, not to the page's own directory.
- Orphan pages — files under wiki/pages/ (any depth) not listed in wiki/index.md (compare normalized wiki-root-relative paths, not bare slugs)
- Missing pages — entries in wiki/index.md pointing to files that don't exist
- Broken internal links — markdown links in pages pointing to non-existent pages; resolve
pages/...link targets from the wiki root - Missing frontmatter — pages lacking required YAML fields (title, tags, created, sources)
- Stale content — pages whose
updateddate is more than 90 days old (flag for review) - Tag inconsistency — tags used in pages but not defined in schema.md conventions
- Index completeness — pages that exist but have no description in the index
- Uncategorized pages (info) — pages sitting flat in wiki/pages/ rather than under a category; valid but suggest moving into a category
- Category consistency (info) — category directories under wiki/pages/ not listed in schema.md
## Categories, or schema categories with no pages yet
Note: the same slug under two different categories (pages/api/auth.md and pages/security/auth.md) is allowed — pages are addressed by full path. Do not report a duplicate-basename collision as an error; at most note it as info if it looks unintentional.
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.
- 2d ago First seen · 64 lines · 14 tokens per session scan A 201a99976974
wiki-lint is a command published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 736 once invoked, about $0.0001 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 commands, from other repositories
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
review
View your learning progress — quiz scores, weak areas, and what to study next.