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/raccioly/docguard/fixgit clone --depth 1 https://github.com/raccioly/docguardWhat 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 | $0.00018 | $0.00599 |
| Opus 5 | $0.00009 | $0.00300 |
| Sonnet 5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
fix 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocGuard Fix
DocGuard splits drift into two kinds and is explicit about which is which.
- Mechanical (deterministic, no AI): apply with
docguard fix --write. Covers removing endpoints documented but absent in code, refreshing stale "N validators" counts, replacing stale version references, inserting a missing## [Unreleased]. - Agent (needs judgment): content rewrites — e.g. updating an X-Ray section to CloudWatch, writing a new endpoint's request/response block.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Execution
Step 1 — Apply mechanical fixes (fast, safe, no AI)
npx --yes docguard-cli@latest fix --write
Output lists every applied fix. Idempotent: re-running is a no-op if nothing changed.
Only edits <!-- docguard:generated true --> docs unless --force.
Step 2 — Identify remaining issues by kind
npx --yes docguard-cli@latest diagnose --format json
Each issue is tagged fixKind: mechanical (mostly handled by step 1) or
fixKind: agent. Focus on the agent ones.
Step 3 — Use the deep doc prompt for content rewrites
For each affected canonical doc, get a research-grounded prompt:
npx --yes docguard-cli@latest fix --doc architecture
npx --yes docguard-cli@latest fix --doc data-model
npx --yes docguard-cli@latest fix --doc api-reference
npx --yes docguard-cli@latest fix --doc security
npx --yes docguard-cli@latest fix --doc test-spec
npx --yes docguard-cli@latest fix --doc environment
Execute the research steps in each prompt: read actual code files, map modules, trace routes, extract real schemas, identify real auth patterns. Then write the sections — using real file paths, real module names, real dependencies. No placeholders.
Step 4 — Verify
npx --yes docguard-cli@latest guard
Iterate until clean (max 3 rounds; if still failing, report remaining issues).
Flags
--write— apply deterministic fixes in place (step 1).--doc <name>— emit a research-grounded prompt for one specific document (step 3).--force— for--write, edit docs that lack the generated marker.--format json— machine-readable issue list (withfixKind).
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 · 75 lines · 18 tokens per session scan A 15805a872b81
fix is a command published in the GitHub repository raccioly/docguard (27 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 599 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
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
/add-claude-rule
Appends the rule from $ARGUMENTS to CLAUDE.md.
implement-regression-tests
Implement regression tests marked with it.skip.
plan-regression-tests
Plan regression tests for existing code with it.skip statements.
ado-pull
Pull latest changes from Azure DevOps (like git pull). Supports increment, project, or full living docs sync.