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/mukul975/threatswarm/reportgit clone --depth 1 https://github.com/mukul975/ThreatswarmWrote 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/mukul975/threatswarm/report)<a href="https://agentmods.dev/commands/mukul975/threatswarm/report"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/report.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 | $0.00010 | $0.00653 |
| Opus 5 | $0.00005 | $0.00327 |
| Sonnet 5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
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 5d 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.
What it actually says
Generate penetration test report named: $ARGUMENTS
-
Setup:
═══════════════════════════════════════════ REPORT GENERATION Name: $ARGUMENTS Output: reports/$ARGUMENTS.md Source: evidence/ directory ═══════════════════════════════════════════Ensure
mkdir -p reports/exists. -
Evidence Discovery: Find all findings files:
- Glob
evidence/**/*findings*.md - Glob
evidence/**/*_report.md - Glob
evidence/**/exploitation.md - Glob
evidence/**/post_ex.md - Glob
evidence/**/ad_findings.md - Glob
evidence/**/web_findings.md - Glob
evidence/**/api_findings.md - Glob
evidence/**/network_findings.md
- Glob
-
Invoke
report-writerAgent: Delegate with:- List of all evidence files found
- Engagement name: $ARGUMENTS
- Read scope.txt for scope section
- Consolidate all findings into the full report template
- Sort findings by CVSS score (critical first)
- Deduplicate overlapping findings
- Write to
reports/$ARGUMENTS.md
-
Quality Check: After writing:
- Count findings by severity
- Verify all CRITICAL findings have CVSS vectors
- Verify all findings have remediation steps
- Check for any [PLACEHOLDER] text left unreplaced
- Verify no plaintext credentials in report (search for common patterns)
-
Print Report Summary:
═══ REPORT COMPLETE ════════════════════════════ File: reports/$ARGUMENTS.md Word count: $(wc -w reports/$ARGUMENTS.md | awk '{print $1}') Pages est.: ~$(wc -w reports/$ARGUMENTS.md | awk '{print int($1/300)}') Findings by severity: Critical: $(grep -c "| CRITICAL |" reports/$ARGUMENTS.md || echo 0) High: $(grep -c "| HIGH |" reports/$ARGUMENTS.md || echo 0) Medium: $(grep -c "| MEDIUM |" reports/$ARGUMENTS.md || echo 0) Low: $(grep -c "| LOW |" reports/$ARGUMENTS.md || echo 0) Info: $(grep -c "| INFO |" reports/$ARGUMENTS.md || echo 0) Top recommendations: [print first 3 critical/high finding titles] Report ready: reports/$ARGUMENTS.md ════════════════════════════════════════════════
If no evidence files are found, output:
⚠ No findings files found in evidence/
Run /project:engage <target> first to collect evidence.
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.
- 5d ago First seen · 71 lines · 10 tokens per session scan A 5455fe080006
report is a command published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 653 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.
Other commands, from other repositories
tachi.security-report
Generate a professional PDF security assessment booklet from tachi pipeline artifacts — auto-detects threats.md (required), threat-report.md, risk-scores.md, compensating-controls.md, and infographic JPEG images, assembles them into a sequenced multi-page PDF using Typst with branded cover, disclaimer, TOC, risk…
open
Open a PDF in the in-app viewer panel.
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.
doc-to-md
Convert a local document (PDF, DOCX, HTML, …) to Markdown, read-only.
read-paper
Read a PDF and auto-generate a structured paper note. Output defaults to unreviewed and must pass /review-note before being citable by the wiki.