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 skills/jansenanalytics/claudex/doc-verifiernpx skills add JansenAnalytics/claudex --skill doc-verifiergit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/doc-verifier)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/doc-verifier"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/doc-verifier.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 | $0.00048 | $0.01084 |
| Opus 5 | $0.00024 | $0.00542 |
| Sonnet 5 | $0.00010 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
doc-verifier 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Verifier
Catches documentation rot before users hit it. Validates everything: code examples actually run, links resolve, API docs match reality, CLI flags exist, and docs stay fresh.
Scripts: ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/doc-verifier/scripts/
Binary: ~/bin/doc-verifier
Quick Reference
S=${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/doc-verifier/scripts
# Full review of a project
doc-verifier ~/my-project
# Quick check (links + freshness only)
doc-verifier ~/my-project --quick
# Full audit including code execution
doc-verifier ~/my-project --full
# With API comparison
doc-verifier ~/my-project --api-url http://localhost:3000
# With CLI comparison
doc-verifier ~/my-project --cli-cmd "node ~/my-project/cli.js"
# Output to separate directory
doc-verifier ~/my-project --output-dir /tmp/doc-review
# JSON format
doc-verifier ~/my-project --format json
# Compare with previous review
doc-verifier ~/my-project --compare /tmp/previous-review
# Individual scripts
node $S/links.cjs ~/my-project
node $S/freshness.cjs ~/my-project
node $S/completeness.cjs ~/my-project
node $S/examples.cjs ~/my-project
node $S/api-docs.cjs ~/my-project --api-url http://localhost:3000
node $S/cli-docs.cjs ~/my-project --cli-cmd "mycli"
node $S/report.cjs /tmp/output-dir --format md
Scripts
1. examples.cjs — Code Example Validator
Extracts fenced code blocks from markdown and executes them:
- bash/sh: Runs commands, checks exit codes. Skips dangerous commands (rm, drop, delete).
- js/javascript: Writes to temp file, runs with Node. Checks syntax/runtime errors.
- python: Writes to temp file, runs with python3.
- Skips blocks marked
<!-- skip-verify -->or data blocks (text, json, yaml, etc.) - Output:
examples-report.json
2. links.cjs — Link Checker
- External URLs: HEAD request, checks status codes
- Internal links: verifies file exists
- Anchor links: verifies heading exists
- Cross-file anchors: verifies both file and heading
- Image references: verifies image exists
- Rate limited (5 req/sec), configurable timeout/retries
- Output:
links-report.json
What ships with it
8 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.
- scripts/api-docs.cjs 4.5 KB runs code
- scripts/cli-docs.cjs 3.1 KB runs code
- scripts/completeness.cjs 4.8 KB runs code
- scripts/examples.cjs 5.1 KB runs code
- scripts/freshness.cjs 5.6 KB runs code
- scripts/links.cjs 5.5 KB runs code
- scripts/report.cjs 4.6 KB runs code
- scripts/review.cjs 2.9 KB runs code
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 · 119 lines · 48 tokens per session scan A a65517a77975
doc-verifier is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,084 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
verify-docs
Periodic doc verification — runs validate.sh structural check, samples assumption rows for semantic review. Run quarterly to collect drift evidence.
data-lake
Use when external catalog queries (Hive, Iceberg, S3, HDFS, Paimon) are failing, hanging, or returning stale data. Covers Hive Metastore connectivity errors, Kerberos authentication failures (keytab expiry, GSS errors, clock skew), S3 rate limiting and SSL issues, network saturation from HMS, and metadata cache TTL…
kibi-freshness
Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.
Golden Master
Track source-of-truth relationships between files — know when derived content becomes stale.
markdown-enhancer
Markdown处理(目录生成、链接检查、表格格式化、统计、Lint、转HTML).
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.