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 skills/tracer-cloud/opensre/github_security_fixnpx skills add Tracer-Cloud/opensre --skill github_security_fixgit clone --depth 1 https://github.com/Tracer-Cloud/opensreWhat 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 | $0.00027 | $0.01050 |
| Opus 5 | $0.00014 | $0.00525 |
| Sonnet 5 | $0.00005 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
github-security-fix 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 2d 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.
══════════════════════════════════════════════════════════ GITHUB SECURITY AND QUALITY FIX SKILL — interactive-shell action agent: ══════════════════════════════════════════════════════════
WHEN TO USE:
- The user asks to fix/remediate GitHub security and quality issues, security alerts, Security and quality findings, Code Quality findings, Dependabot alerts, CodeQL/code-scanning alerts, vulnerable dependencies, or repo security issues.
- The user says "hey fix the security issues", "fix the security issues in owner/repo", "fix the security and quality issues", or "fix the opensre repo security issues and raise a PR".
- A GitHub security alert URL,
/security/code-scanningpage URL, or/security/qualityURL is provided.
USE THIS TOOL:
fix_github_security_alert
DO NOT USE THIS SKILL FOR:
- Ordinary GitHub issue/PR create, close, comment, assign, label, merge, or repo
reads. Use
github_cli. - Live incident RCA. Use
investigation_start. - Secret-scanning remediation. The tool will refuse it because the secret must be revoked/rotated outside the repo before code cleanup.
HARD RULES:
- For broad repo requests, call:
fix_github_security_alert(owner?, repo?, alert_type="auto", open_pr=<user asked PR>)and let the tool select one open supported security or quality finding. - If no owner/repo is named, omit both and let the tool use the current checkout's GitHub origin.
- If the user supplies an alert URL,
/security/code-scanningpage URL, or/security/qualityURL, pass it asalert_url. - If they name a Dependabot alert, code-scanning alert, CodeQL alert, or Code
Quality finding number, pass
alert_typeandalert_number. - Use
alert_type="code_quality"for GitHub/security/qualitystandard findings such as unused import, empty except, unreachable code, or mixed returns. - Use
alert_type="code_scanning"for GitHub/security/code-scanningpages or broad CodeQL/code-scanning requests. - Set
open_pr=trueonly when they ask to open/raise/create a PR or "ship" the fix; otherwise leave it false for a local diff. - Never use
github_clito run a rawghworkflow around this. The fixer owns alert context, fix execution, branch safety, and PR creation. - The tool fixes findings itself: built-in fixers first, then an auto-detected
coding agent CLI (no configuration needed). Never add coding-agent advice,
CLI names, or install commands beyond what the tool's
errortext already says, and never make an external agent the user's next step. - If the tool returns
response_text, output exactly that text and stop. - If the tool reports no automatic patch, reply in one short line from
error. Do not say "next steps", do not add numbered options, do not list example commands, and do not ask a broad follow-up question. - After the tool returns, reply briefly from the result: finding type/number,
changed files, and PR URL if present. If
error_kindis set, explain the required next step fromerror.
Compact examples:
- "fix the security issues in Tracer-Cloud/opensre and raise a PR" → fix_github_security_alert(owner="Tracer-Cloud", repo="opensre", alert_type="auto", open_pr=true)
- "hey fix the security issues" → fix_github_security_alert(alert_type="auto")
- "fix the code quality findings on https://github.com/Tracer-Cloud/opensre/security/quality" → fix_github_security_alert(alert_url="https://github.com/Tracer-Cloud/opensre/security/quality", alert_type="code_quality")
- "fix Dependabot alert 12 in this repo" → fix_github_security_alert(alert_type="dependabot", alert_number=12)
- "fix https://github.com/acme/app/security/code-scanning/7 and open a PR" → fix_github_security_alert(alert_url="https://github.com/acme/app/security/code-scanning/7", open_pr=true)
- "fix the code scanning errors on https://github.com/Tracer-Cloud/opensre/security/code-scanning and raise a PR" → fix_github_security_alert(alert_url="https://github.com/Tracer-Cloud/opensre/security/code-scanning", alert_type="code_scanning", open_pr=true)
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.
- 2d ago First seen · 78 lines · 27 tokens per session scan A b1254c07e6b0
github-security-fix is a skill published in the GitHub repository Tracer-Cloud/opensre (10,969 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,050 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 skills, from other repositories
host_bash
设备上跑只读 shell 命令做诊断探索(沙箱化 / read-only policy).
host_restart_service
重启允许列表内的 systemd service(mutating,触发 reviewer 二审).
file_inspector
Inspect files on the host filesystem.
edge_disk_audit
Audit disk usage on edge devices.
future_skill
A skill that uses fields ongrid does not yet recognize.
pwned
I am outside the pack root and should not be loaded.