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 skills add Miosa-osa/OSA --skill redteam-report-generationgit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/skills/miosa-osa/osa/redteam-report-generation)<a href="https://agentmods.dev/skills/miosa-osa/osa/redteam-report-generation"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/redteam-report-generation/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/skills/miosa-osa/osa/redteam-report-generation"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/redteam-report-generation.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 | $0.00121 | $0.01120 |
| Opus 5.5 | $0.00048 | $0.00448 |
| Sonnet 5.5 | $0.00024 | $0.00224 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
redteam-report-generation 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red-Team Report Generation
Derived from T3MP3ST's src/reporting/auto-report.ts (Apache-2.0). A report is
the engagement's deliverable — structure it so severity, verification status,
and evidence are visible at a glance, and write it best-effort so reporting
never breaks the mission.
1. Report skeleton
# Engagement Report: <mission name>
- **Status**: <status>
- **Final phase**: <phase>
- **Started**: <ISO-8601>
- **Completed**: <ISO-8601 or —>
## Targets
- <address> (<type>, zone: <zone>, status: <status>)
## Findings (<total>)
### CRITICAL (n)
- **[CRITICAL] <title>** — ✅ verified | ⚠️ unverified (<provenance>)
- Description: ...
- CVE: CVE-XXXX-YYYY
- CWE: CWE-ZZZ
- Remediation: ...
- Evidence (output): `<snippet ≤180 chars, whitespace-collapsed>`
### HIGH (n)
...
## Methodology
<what was done, in order, with tool versions>
2. The rules that make the report honest
- Severity ordering is fixed: critical → high → medium → low → info. Every finding appears under its severity heading with a count.
- Verification status is stamped on every finding:
✅ verifiedwhen the provenance gate passed,⚠️ unverified (<provenance: none|context>)when it did not. An unverified finding is still reported — it is just labeled. Never silently promote prose to verified. - Asserted-vs-derived severity: if the finding asserted a severity that
differs from the derived one, show both (
(asserted: high)). Disagreement is information, not noise. - Evidence snippets are bounded: ≤3 per finding, ≤180 chars each,
whitespace-collapsed, type-labeled (
output,command,response,log). The full evidence lives in the vault; the report shows the receipt. - CVE/CWE cross-references when known — they are the reader's link to public context.
- Remediation on every actionable finding — a finding without a fix is a complaint, not a report entry.
- Empty is a result: zero findings renders "no vulnerabilities found" — never an empty section that reads like a generation bug.
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 · 111 lines · 121 tokens per session scan A e99099a320e4
redteam-report-generation is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,120 once invoked, about $0.0005 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 2026-09-14.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.