Borrowing it
Nothing to install: this file belongs to obot-platform/obot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/obot-platform/obot/main/.claude/skills/rewrite-security-advisory/SKILL.mdgit clone --depth 1 https://github.com/obot-platform/obotWrote 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/obot-platform/obot/rewrite-security-advisory)<a href="https://agentmods.dev/skills/obot-platform/obot/rewrite-security-advisory"><img src="https://agentmods.dev/badge/skills/obot-platform/obot/rewrite-security-advisory.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 5.1 | $0.00087 | $0.01259 |
| Opus 5 | $0.00044 | $0.00629 |
| Sonnet 5 | $0.00017 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
rewrite-security-advisory 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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rewrite Security Advisory
Take a verbose, reporter-submitted obot security advisory and rewrite it into Obot's concise, user-facing format. The goal is a short writeup a deployer can read and immediately know whether they're affected and what to do — not a reproduction of the researcher's full report.
Output is a markdown file at the repo root named <GHSA-id>.md. The user reviews
it and pastes it into the GitHub advisory editor themselves. Do not push it to
GitHub or modify the live advisory unless explicitly asked.
1. Fetch the advisory
The advisory is usually a private draft, so the web URL 404s for WebFetch. Pull it via the authenticated API instead:
gh api repos/obot-platform/obot/security-advisories/<GHSA-id> --jq '{summary, description, severity, cvss: .cvss.vector_string, score: .cvss.score, vuln_range: .vulnerabilities[0].vulnerable_version_range, patched: .vulnerabilities[0].patched_versions, credits: [.credits_detailed[].user.login], cwes: [.cwes[].cwe_id]}'
This gives you the title, the reporter's full description (Summary/Details/PoC/Impact), CVSS vector + score, affected range, and the credited reporters.
2. Read the comments — they matter
The advisory's comment thread is NOT exposed by the GitHub API (REST or GraphQL), and the web page 404s for WebFetch on drafts. Ask the user to paste the comments, especially the obot team's response (often from the lead eng). The comments frequently change the framing — e.g. clarifying that the reporter's headline mechanism was actually a fail-safe and the real fix was something else, or noting which parts were disputed. Do not finalize the rewrite without them.
3. Confirm the patched version
The advisory's patched field is often empty and vuln_range may be recorded as
a commit hash. Always express versions as release tags, never commit hashes
(users reason about releases, not commits). Ask the user which release contains
the fix if it isn't obvious; the affected range is then <= <last release before the fix> (e.g. fixed in v0.23.0 → affected <= v0.22.1).
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.
- 6d ago First seen · 93 lines · 87 tokens per session scan A e71fcb526cf9
rewrite-security-advisory is a skill published in the GitHub repository obot-platform/obot (978 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,259 once invoked, about $0.0004 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 skills, from other repositories
prompt-design
Design MCP prompts to expose reusable prompt templates. Use when creating parameterized prompts in xmcp.
claude-code-dmwork
Connect to DMWork messaging platform as an AI bot via the OpenClaw DMWork adapter plugin.
octocode-brainstorming
Use when an idea needs disciplined exploration before building: generate options, test whether it is worth building, map adjacent solutions, challenge assumptions, narrow scope, or choose Build RFC / Prototype / Narrow / Park — even if nobody said brainstorm. Already decided to implement a specific plan → skip.
octocode-chrome-devtools
Use when a live page needs Chrome DevTools/CDP evidence: network failures, console errors, performance, DOM/CSS actionability, screenshots/PDF, cookies/storage, click/fill/search, HAR, or auth-gated pages. Phrases like debug in Chrome, live page health, CDP snapshot, cookie bridge. Not for static crawl or bulk extract…
octocode-graph-eval
Use when you need a measurable keep/discard loop — goal→KPI, baseline vs target, held-out checks, eval suites, or don't-stop-till-done against a runnable sensor. Not for ordinary ship checks where 'tests passed' is enough.
octocode-subagent
Use when spawning workers or offloading work: Task/subagents, specialist handoffs, A2A peers, sealed packets, coordinate/synthesize, challenge techniques (rubber-duck, interview, mimic-flow, red-team, blind review, consensus), or local Ollama one-shots to save tokens. Measuring keep/discard KPIs → octocode-graph-eval.