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/omermaksutii/RugProofWrote 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/omermaksutii/rugproof/report)<a href="https://agentmods.dev/commands/omermaksutii/rugproof/report"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/report/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/omermaksutii/rugproof/report"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/report.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 | $0.00020 | $0.00725 |
| Opus 5.5 | $0.00008 | $0.00290 |
| Sonnet 5.5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
report 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/report — generate audit deliverable
Take the most recent /audit (or /audit-deep) result and render it as a deliverable. Default formats from .rugproof.yml report.formats.
Procedure
Step 1 — Locate findings
If a recent audit isn't in conversation context, ask the user to run /audit first, or point them at rugproof-reports/findings.json if it exists.
Step 2 — Build the report sections
- Executive summary — 4-6 sentences. Lead with the dollar value at risk, the number of Critical findings, and the trust level. Suitable for executives.
- Severity overview — counts table, grade.
- Trust report (centralization findings) — from [[centralization-risk]] format.
- Findings — one section per finding, sorted by severity descending:
- Title, ID, severity, confidence
- File path:line + code block of the offending lines
- Description (what / how / why)
- Impact + likelihood
- Remediation patch (diff)
- Historical context if any
- Methodology — which skills ran, which specialist subagents dispatched, scope (lines audited).
- Out of scope / known limitations — be honest about what wasn't checked.
- Appendix — tool versions, MCP server versions, git commit, contract addresses.
Step 3 — Dispatch report-writer subagent
For long reports, dispatch the report-writer subagent with the raw findings — it will produce polished prose without consuming the main context.
Step 4 — Render formats
For each requested format, use the corresponding template in templates/:
- markdown →
templates/report.md.hbs→rugproof-reports/audit-YYYY-MM-DD.md - html →
templates/report.html.hbs→ styled, navigable, collapsible sections - pdf → render HTML through headless Chrome / wkhtmltopdf
- json → structured findings + metadata for CI / dashboards
- png →
templates/audit-card.svg.hbs→ run throughresvgorsharp(use/cardinternally)
Step 5 — Output
Tell the user where the files are:
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.
- 1mo ago First seen · 65 lines · 20 tokens per session scan A 5fe515538de2
report is a command published in the GitHub repository omermaksutii/RugProof (10 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 725 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
octo-docs
Document delivery with export to PPTX, DOCX, PDF formats.
doc-to-md
Convert a PDF, docx, image, or other document to clean Markdown using Antigravity (agy) multimodal Gemini. Saves to docs/agy/converted/.
docs
Document delivery with export to PPTX, DOCX, PDF formats.
print-export-designer
Use when something has to leave the screen. PDF generation, print stylesheets, receipts and invoices, exported reports, or a download that gives the user no feedback.
ssp-guidance
System Security Plan (SSP) documentation guidance.
paper-trail-inject-url
Injecte une URL OA connue (HAL, dépôt uni, NIME, page perso) pour une ref dont la cascade automatique a échoué, puis relance l'acquisition + validation page 1.