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 cosai-oasis/secure-ai-tooling --skill draft-issue-commentgit clone --depth 1 https://github.com/cosai-oasis/secure-ai-toolingWrote 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/cosai-oasis/secure-ai-tooling/draft-issue-comment)<a href="https://agentmods.dev/skills/cosai-oasis/secure-ai-tooling/draft-issue-comment"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/draft-issue-comment/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/cosai-oasis/secure-ai-tooling/draft-issue-comment"><img src="https://agentmods.dev/badge/skills/cosai-oasis/secure-ai-tooling/draft-issue-comment.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 | $0.00107 | $0.00732 |
| Opus 5.5 | $0.00043 | $0.00293 |
| Sonnet 5.5 | $0.00021 | $0.00146 |
| Haiku 4.5 | $0.00011 | $0.00073 |
Grade A, and why
draft-issue-comment 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 15d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Issue Review Comment
Source of truth: the review process, field-by-field feedback, output structure, and quality gates live in the canonical agent spec
scripts/agents/issue-response-reviewer.md(which composescontent-reviewerinissuemode). This skill applies that spec; it does not restate its rules. Duplicating the spec here is what let an earlier version drift stale — this skill stays thin and lets the canonical spec remain the authority.
Produce a structured maintainer review comment for a GitHub issue proposing new or updated CoSAI-RM content, written to a local file for the maintainer to edit and post manually (this skill produces a local draft and does not post to GitHub).
Steps
- Load the review spec. Read
scripts/agents/issue-response-reviewer.mdand follow it — it defines the review workflow, the field-by-field feedback structure, the output template, and the quality gates. Do not re-derive these here. - Gather issue context:
gh issue view <number> --repo cosai-oasis/secure-ai-tooling --json title,body,author,createdAt,labels,commentsgh api repos/cosai-oasis/secure-ai-tooling/issues/<number>/commentsfor any discussion- Determine the issue type (
risk|control|component|persona) from the issue's template label / title prefix, or the--typeargument. - Read the relevant
risk-map/yaml/*.yamlfor overlap analysis, and the style guides the canonical spec names for that type.
- Produce the review following the canonical spec's output structure and quality gates.
- Write the draft to
draft-<issue-number>-comment.mdin the repo root. It is a local draft; the maintainer edits and posts it.
Operational notes
- Local output only. This skill writes a local draft; the maintainer posts it manually.
- Citations follow the canonical spec's rules (ADR-016/017), not a copy of them here. The earlier drift bug this skill was rewritten to fix was exactly an inline HTML-anchor citation rule going stale — do not reintroduce field-level citation mechanics in this file; read them from
issue-response-reviewer.mdeach time. - Keep this skill thin. If the review logic changes, update
scripts/agents/issue-response-reviewer.md(the authority), not this file.
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.
- 15d ago First seen · 34 lines · 107 tokens per session scan A 2c6dd3905d08
draft-issue-comment is a skill published in the GitHub repository cosai-oasis/secure-ai-tooling (100 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 732 once invoked, about $0.0004 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 2026-10-01.
Other skills, from other repositories
svc-mobile-android
Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.
svc-pivoting
Turn a foothold into a RELIABLE pivot (SOCKS tunnel + persistent shell) so internal volume never rides a fragile stateless RCE. Use the moment you have code-exec on a dual-homed/edge host and need to reach an internal segment. Triggers - dual-homed host, "not reachable from my box", internal CIDR behind a foothold…
web-auth-bypass-idor
Broken access control - IDOR, privilege escalation, JWT abuse, mass assignment, forced browsing - for web apps and APIs. Use on any multi-user or role-based app with object IDs, tokens, or admin functionality. Triggers - /api/users/ , /orders/ , ?account=/uid=/doc=, JWT (eyJ...), role/isAdmin field, admin panel, "403…
web-deserialization
Insecure deserialization to RCE for web apps. Use when the app deserializes attacker-controlled data - cookies/tokens/hidden fields/params that are serialized blobs, VIEWSTATE, Java/PHP/.NET/Python/Node apps. Triggers - base64 starting rO0AB or hex AC ED 00 05 (Java), PHP serialize O-prefix, VIEWSTATE, python pickle…
web-lfi-traversal
Path traversal / Local File Inclusion detection→file-read→RCE for web apps. Use when a param names a file/path/page/template/lang/download, or a response embeds file contents. Triggers - file=/page=/path=/template=/lang=/download=/include= param, ../, %2e%2e, "no such file", directory listing, download endpoint.
web-sqli
SQL injection detection→exploitation→proof for web apps and APIs. Use when a parameter reaches a DB query, when input triggers a SQL error / boolean or time differential, or during VULN-ASSESSMENT/EXPLOITATION on a web target. Triggers - sql syntax error, ORA-/MySQL/psql/SQLite error string, ' or 1=1, order by…