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/preflight)<a href="https://agentmods.dev/commands/raccioly/docguard/preflight"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/preflight/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/preflight"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/preflight.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 | $0.00010 | $0.00441 |
| Opus 5.5 | $0.00004 | $0.00176 |
| Sonnet 5.5 | $0.00002 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
preflight 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 Generated-Spec Preflight
Run after the specification exists and before planning or task generation. The generated draft is the reviewable artifact that DocGuard can gate.
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
Execution
-
Resolve the current feature's
spec.md. Use an explicit path from the user when supplied. Otherwise use the current Spec Kit feature directory; its prerequisite script reportsFEATURE_DIRin JSON. Use the platform-specific script under.specify/scripts/and append/spec.md. -
Confirm the draft declares a stable metadata field near the top:
**Spec ID**: `organization.feature-name`
Add a project-scoped lowercase ID when it is missing. Never reuse an ID from the briefing, even when an old spec has moved to Git history.
- Run the read-only generated-spec gate:
docguard specs preflight --path <feature-spec.md> --format json
-
If the result is
BLOCKED, stop before task generation. Fix duplicate or missing identity, broken lineage, unsafe paths, or stale registry state, then rerun the same command. -
Review
overlapsmanually. Similarity has low confidence and never blocks by itself. Record a reviewedextends,duplicates,conflictsWith,supersedes, orsupersededByrelation only when the underlying intent supports it. -
Continue only when the deterministic status is
READY. Refresh the registry after the draft is accepted so CI observes its current digest and requirement identities:
docguard specs --write
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 611fc3b9df44
- 3d ago Changed 79927aefbc2f
- 5d ago Changed a62550862194
- 6d ago Changed 4cf6fad4ee4b
- 15d ago Changed · +6 lines abe2819a5743
- 1mo ago First seen · 53 lines · 10 tokens per session scan A e2b53333fa5a
preflight is a command published in the GitHub repository raccioly/docguard (32 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 441 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
check-task.en
Check a task's current status and progress.
init-milestones.en
Initialize the repository's standard milestones taxonomy.
aigon-feedback-triage
Run a triage loop for one feedback item with explicit human confirmation before writes.
aigon-research-context
Record the original author's durable, transcript-free handoff.
speckit.gh-triage.feature
Create a GitHub issue describing a new feature, label it with the configured feature label, and optionally auto-run speckit.specify to turn it into a spec.
analytics-review
Review analytics and recent commits, then create tasks.