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/davidmoneil/aifred-document-guard/statusgit clone --depth 1 https://github.com/davidmoneil/aifred-document-guardWrote 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/davidmoneil/aifred-document-guard/status)<a href="https://agentmods.dev/commands/davidmoneil/aifred-document-guard/status"><img src="https://agentmods.dev/badge/commands/davidmoneil/aifred-document-guard/status.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00581 |
| Opus 5 | $0.00007 | $0.00291 |
| Sonnet 5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
status scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -5 .claude/logs/document-guard.jsonl 2>/dev/null || echo "No audit log found" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/document-guard:status
Show the current state of Document Guard.
Instructions
Run the following diagnostic steps and present results:
1. Config Source
Check which config is active:
node -e "
const fs = require('fs');
const path = require('path');
const projectDir = process.env.CLAUDE_PROJECT_DIR || process.cwd();
const projectConfig = path.join(projectDir, '.claude', 'hooks', 'document-guard.config.js');
const pluginRoot = '${CLAUDE_PLUGIN_ROOT}' !== '' ? '${CLAUDE_PLUGIN_ROOT}' : path.resolve(__dirname, '..');
const pluginConfig = path.join(pluginRoot, 'config', 'document-guard.config.js');
let source = 'none';
if (fs.existsSync(projectConfig)) source = 'project: ' + projectConfig;
else if (fs.existsSync(pluginConfig)) source = 'plugin-default: ' + pluginConfig;
console.log('Config source: ' + source);
"
2. Current Settings
Read the active config file identified above. Report:
- V1 enabled: yes/no
- Credential scan: yes/no
- Structural checks: yes/no
- V2 (semantic): yes/no
- Fail mode: open/closed
- Override TTL: N seconds
3. Active Rules Table
List all rules from the config in a table:
| Tier | Rule Name | Pattern | Checks |
|---|---|---|---|
| critical | ... | ... | ... |
4. Recent Audit Log
Read the last 5 entries from .claude/logs/document-guard.jsonl (if it exists):
tail -5 .claude/logs/document-guard.jsonl 2>/dev/null || echo "No audit log found"
Format each entry showing: timestamp, action (blocked/warned/override_used), file, violations.
5. Active Overrides
Check .claude/logs/.document-guard-overrides.json for any active overrides:
cat .claude/logs/.document-guard-overrides.json 2>/dev/null || echo "No active overrides"
6. Creating a Project Override
If the user wants to customize rules, explain:
To create a project-specific config, copy the plugin default and modify it:
mkdir -p .claude/hooks cp <plugin-config-path> .claude/hooks/document-guard.config.jsThe project config takes full precedence over the plugin default.
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.
- 3d ago First seen · 83 lines · 14 tokens per session scan A f9e929ce24d5
status is a command published in the GitHub repository davidmoneil/aifred-document-guard (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 581 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
ai-act-incidents
Show real-world and research-demonstrated security incidents that map to a scanner dimension, EU AI Act article, or threat category. Surfaces OWASP LLM/ASI, NIST AI RMF, and MITRE ATLAS cross-references alongside published mitigations.
ai-act-scan
Scan a codebase for EU AI Act compliance evidence and gaps. Produces a dimension-scored report with per-file findings, architecture graph, and prioritized recommendations.
ai-act-article
Show which analyzers, compliance dimensions, and current findings in this codebase map to a specific EU AI Act article.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
ai-act-settings
View or change the scanner's settings — mode (deterministic vs assisted) and autoapply. Assisted mode lets the plugin use your own Claude Code for semantic scanning, grounded Q&A, and applying fixes.
start-issue
You are beginning work on GitHub issue $ARGUMENTS.