diagnose

A documentation-diagnosis command that checks a project and turns documentation problems into suggested repair instructions.

In plain words
What is it for?
Use it to inspect issues, view an ordered repair plan, request three-perspective analysis with `--debate`, or receive JSON output.
Why use it?
It makes unclear documentation failures easier to understand and gives an AI coding agent a prompt for addressing them.

Command

Install

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.

agentmods
npx agentmods add commands/raccioly/docguard/diagnose
Clone the repo
git clone --depth 1 https://github.com/raccioly/docguard
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 289 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00289
Opus 5 $0.00005 $0.00144
Sonnet 5 $0.00002 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 3d ago against content hash a614b91a27dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnose 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 3d 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.

extensions/spec-kit-docguard/commands/diagnose.md · 44 lines

What it actually says

DocGuard Diagnose

Runs guard validation, analyzes failures, and generates AI-ready prompts to fix documentation issues.

User Input

$ARGUMENTS

Steps

  1. Run DocGuard diagnose on the current project:
npx --yes docguard-cli@latest diagnose $ARGUMENTS
  1. Review the output:

    • Issues found — categorized as errors or warnings
    • Remediation plan — ordered list of fix commands
    • AI-ready prompt — copy/paste to your AI agent for automated fixes
  2. For multi-perspective analysis, add --debate to get three-agent prompts (Advocate/Challenger/Synthesizer).

Flags

  • --format json — Output as JSON
  • --debate — Generate multi-perspective AI prompts
  • --dir <path> — Run on a different directory

Research

Inspired by AITPG (IEEE TSE 2026) multi-agent prompting and TRACE (IEEE TMLCN 2026) calibrated quality evaluation.

Changes

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.

  1. 3d ago First seen · 44 lines · 10 tokens per session scan A a614b91a27dc

Subscribe to this mod's changes

diagnose is a command published in the GitHub repository raccioly/docguard (27 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 289 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.