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 nirecom/agents --skill scan-offensivegit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/scan-offensive)<a href="https://agentmods.dev/skills/nirecom/agents/scan-offensive"><img src="https://agentmods.dev/badge/skills/nirecom/agents/scan-offensive/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/nirecom/agents/scan-offensive"><img src="https://agentmods.dev/badge/skills/nirecom/agents/scan-offensive.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 | $0.00023 | $0.01130 |
| Opus 5.5 | $0.00009 | $0.00452 |
| Sonnet 5.5 | $0.00005 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
scan-offensive 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/scan-offensive
Scan a GitHub repository's issues and comments for offensive content
(hate speech, slurs, harassment, profanity). Produces a JSONL manifest;
CC evaluates each item inline. Companion to the forward filter in
hooks/scan-outbound.js, which blocks offensive content at write time.
Arguments
| Flag | Default | Meaning |
|---|---|---|
<owner>/<repo> |
current repo (gh repo view) |
Target repository |
--dry-run |
on | Produce manifest only; do not edit |
--apply |
off | Redact confirmed items (canary-gated; requires --manifest-path + --confirm-ids) |
--since YYYY-MM-DD |
none | Restrict to issues updated after this date (server-side) |
--until YYYY-MM-DD |
none | Restrict to issues updated before this date (client-side) |
--from-issue N |
none | Scan only issues numbered >= N |
--to-issue N |
none | Scan only issues numbered <= N |
--manifest-out PATH |
stdout | Write JSONL manifest to PATH instead of stdout |
--manifest-path FILE |
— | (with --apply) Path to previously produced manifest |
--confirm-ids ID,... |
— | (with --apply) Comma-separated item IDs to redact |
--canary-skip |
off | Skip canary stop; redact all confirmed IDs in one pass |
--limit N |
none | Stop after scanning N issues |
--include-private |
off | Also scan private repos (default skips them) |
Procedure
Phase 1 — Produce manifest
- Resolve
<owner>/<repo>from arguments orgh repo view --json owner,name. - Invoke
scripts/scan-repo.sh <owner>/<repo> [range flags] --manifest-out <tmp.jsonl>.- For large repos, use
--since,--until,--from-issue,--to-issueto scan in batches of <= 100 items.
- For large repos, use
- Confirm the first line of
<tmp.jsonl>has"type":"preamble"and"schema":"scan-offensive/skill-manifest/v1".
Phase 2 — Inline CC evaluation
- Read each item record from
<tmp.jsonl>. For each record where"type":"item":- Extract the
envelopefield. - The body between
<content>and</content>is the scanned issue/comment text. - Un-escape the body using the three-step inverse in this exact order: (1)
>→>, (2)<→<, (3)&→&. - Apply the classification rubric below to the un-escaped body.
- Record a verdict tuple
{id, verdict, reason}.
- Extract the
- Classification rubric:
block: hate speech (slurs, dehumanizing language targeted at a group), personal threats / calls to violence, sustained profanity directed at a person.warn: borderline profanity, ambiguous hostility.clean: no offensive content.keyword_verdict: "hard"is a strong prior; verify the match is not quoted/contextual (e.g., CVE description quoting a slur, discussing the word itself).keyword_verdict: "warn"is a weak prior; require semantic confirmation.keyword_verdict: "clean"with no semantic match → verdictclean.
- Present findings (verdict ≠
clean) to the user with source URL.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 78 lines · 23 tokens per session scan A 9fdad2223a8d
scan-offensive is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,130 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…