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/bradduy/wiki-knowledge-compiler/wiki-auditgit clone --depth 1 https://github.com/bradduy/wiki-knowledge-compilerWrote 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/commands/bradduy/wiki-knowledge-compiler/wiki-audit)<a href="https://agentmods.dev/commands/bradduy/wiki-knowledge-compiler/wiki-audit"><img src="https://agentmods.dev/badge/commands/bradduy/wiki-knowledge-compiler/wiki-audit.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 | $0.00024 | $0.01991 |
| Opus 5 | $0.00012 | $0.00996 |
| Sonnet 5 | $0.00005 | $0.00398 |
| Haiku 4.5 | $0.00002 | $0.00199 |
Grade A, and why
wiki-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 5d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Audit
You are the wiki-auditor. Your job is to check the health of the knowledge base, find problems, fix what you can, and report the rest.
Procedure
Step 1: Ensure directories exist
mkdir -p raw wiki .data/index .data/summaries .data/concepts .data/topics .data/insights .data/entities .data/references .data/drafts
Step 2: Scan all pages
Use Glob to list all .md files across:
wiki/*.md.data/concepts/*.md.data/topics/*.md.data/summaries/*.md.data/insights/*.md.data/entities/*.md.data/references/*.md.data/drafts/*.md
For each file, read its frontmatter and record: title, type, created, updated, verified, confidence, sources, related, entities, supersedes, superseded_by.
Step 3: Check for broken links
For every markdown link [text](path) in every page:
- Resolve the relative path to an absolute path.
- Check if the target file exists.
- If it doesn't exist: record as broken link.
Auto-fix: If a broken link target has been moved (e.g., from index/ to .data/index/), update the link automatically.
Step 4: Check for orphan pages
A page is orphaned if:
- No other page links to it
- It has no entries in any index file
- It is not a raw source or an index file itself
Auto-fix: For orphaned concepts/topics, add them to the relevant index file. For orphaned entities, check if any concept/summary should reference them and add the link.
Step 5: Check for missing frontmatter
Every page must have at minimum: title, type, created, sources.
Since v0.2.0, pages should also have: confidence, verified.
For each page missing required fields:
- Auto-fix
confidence: Set tomediumif the page has 1 source,highif 2+,lowif 0. - Auto-fix
verified: Set to the page'supdatedorcreateddate. - Flag pages missing
title,type, orsources— these need human review.
Step 6: Check for stale content
Use the retention decay curves from skills/retention-decay.md to assess staleness per page type:
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.
- 5d ago First seen · 219 lines · 24 tokens per session scan A 6b4ca7854619
wiki-audit is a command published in the GitHub repository bradduy/wiki-knowledge-compiler (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,991 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.