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/complete)<a href="https://agentmods.dev/commands/raccioly/docguard/complete"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/complete/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/complete"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/complete.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 | $0.00009 | $0.00461 |
| Opus 5.5 | $0.00004 | $0.00184 |
| Sonnet 5.5 | $0.00002 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
complete 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocGuard Spec Completion Review
Run after implementation or convergence. This hook plans the lifecycle gate; it does not mark the feature verified without a reviewed rationale.
- Resolve the current feature
spec.mdand read itsSpec IDmetadata. - Run
docguard guard --format json. Stop on errors. - Refresh deterministic evidence with
docguard specs --write, then review and commit that projection with the implementation. - Select the Git baseline that covers the implementation changes. Prefer the registry's prior reconciliation revision; otherwise use the feature branch's merge base with its configured default branch.
- Run:
docguard specs complete --id <spec-id> --since <ref> --check --format json
If SPC002 reports that the spec is not approved or its delivery is
planned, ask the maintainer to approve it. Never approve on your own:
docguard specs approve --id <spec-id> --delivery implemented --write
- Review every reconciliation classification. Unsupported or ambiguous changes block completion. A possible implementation regression requires deciding whether to fix code, amend approved intent, or record an accepted deviation.
- When the evidence is complete, present the exact reviewed write command to the maintainer. Apply it only when the maintainer supplies the rationale:
docguard specs complete --id <spec-id> --since <ref> --write --reason "<reviewed outcome>"
The write records the outcome, advances delivery through implemented to
verified, and regenerates .docguard/current-context.json as one staged,
post-validated set. In-process write or validation failures roll the set back;
the command does not claim a durable journal across power loss or forced
termination.
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.
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 d32c05f9fe03
- yesterday Changed 86f6b7eb29f5
- 10d ago Changed · +7 lines 0ce35c15cf52
- 11d ago Changed · +7 lines 8b438d831efa
- 27d ago First seen · 39 lines · 9 tokens per session scan A d4b2e721a43b
complete is a command published in the GitHub repository raccioly/docguard (32 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 461 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 2026-09-15.
Other commands, from other repositories
execute-work-packet
Execute a single work packet: verify dependencies, run TDD task loop through three gates, write completion marker.
aitask-run-gates
Run a task's declared gates — the conversational front of the headless gate orchestrator engine. Dispatches unlocked machine-gate verifiers within their retry budgets, observes human gates without self-signalling, and reports.
next
Suggest the most likely next workflow action based on current context.
afo
Open feature worktree in terminal and start agent (shortcut for feature-open).
build
Segment BUILD: implement the approved plan → scripts/check green. Always stops with evidence.
aigon-research-context
Record the original author's durable, transcript-free handoff.