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.
git clone --depth 1 https://github.com/raccioly/docguardWrote 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/raccioly/docguard/review)<a href="https://agentmods.dev/commands/raccioly/docguard/review"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/raccioly/docguard/review"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00008 | $0.00478 |
| Opus 5.5 | $0.00003 | $0.00191 |
| Sonnet 5.5 | $0.00002 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
review 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 today.
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.
What it actually says
DocGuard Review
Perform a read-only semantic review of canonical documentation against the repository. Report evidence and recommendations; do not edit files.
Running DocGuard
Run docguard from PATH when it is installed. Otherwise run
npx --yes [email protected], the release these instructions ship with, in its
place. Every docguard … command below means one of the two.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding when it is not empty.
Execution
-
If any doc section declares
covers=, list which covered sections changed since their last review (read-only):docguard review --format jsonReport every section that is not
current. Do not runreview --accepton the user's behalf: accepting records that a person checked the prose. -
Run the deterministic inventory and quality checks:
docguard diagnose $ARGUMENTS
docguard diff $ARGUMENTS
docguard score $ARGUMENTS
docguard verify --evidence --format json $ARGUMENTS
docguard verify --semantic $ARGUMENTS
- Read the canonical documents and their cited code. Check architecture, schemas, security claims, test coverage, terminology, and cross-references.
- For every contradiction, identify whether approved documentation or current code owns the intended behavior. A mismatch can be a code regression.
- Return a severity-ranked report with exact file paths, evidence, confidence, and a proposed next action. Keep unsupported claims explicitly unverified.
Constraints
- Do not modify files or treat a clean structural guard as proof that prose is factually correct.
- Do not rewrite canonical intent to match code until ownership is resolved.
- Cap the report at 50 findings and aggregate lower-priority overflow.
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.
- today Changed 1875b1ed7dce
- 3d ago Changed 63e9c729ba12
- 5d ago Changed f930a9c173e6
- 6d ago Changed 894457d0566c
- 15d ago Changed · +6 lines 59b45712b4da
- 16d ago Changed · +11 lines bba1d43acb60
- 1mo ago First seen · 51 lines · 8 tokens per session scan A 2373609eae81
review is a command published in the GitHub repository raccioly/docguard (32 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 478 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-16.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
code-review-give
Give mode for code-review: Review someone else's code with multi-pass analysis and structured recommendations.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
review-design-verify
Phases 4-5 of reviewing-design-docs: Interface Verification + Implementation Simulation.
plan-levels
At standard and lean, each row sets one phase's spawns. A phase with no row runs as written. A row only removes or merges agents.