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 mitodl/agent-kit --skill renovate-security-triagegit clone --depth 1 https://github.com/mitodl/agent-kitWrote 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/mitodl/agent-kit/renovate-security-triage)<a href="https://agentmods.dev/skills/mitodl/agent-kit/renovate-security-triage"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/renovate-security-triage.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 | $0.00157 | $0.04539 |
| Opus 5 | $0.00078 | $0.02269 |
| Sonnet 5 | $0.00031 | $0.00908 |
| Haiku 4.5 | $0.00016 | $0.00454 |
Grade A, and why
renovate-security-triage 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 7d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Renovate Security Triage
Turns an org-wide flood of Renovate PRs into a short, ranked list of the ones that matter to you. The pattern is scope → enumerate → enrich → score → rank → report, with five scripts doing the mechanical work and the model supplying the judgment that advisory metadata cannot.
Calibration from a real mitodl run: 436 open Renovate PRs org-wide across 78 repos → 175 PRs in the user's 21 active repos → 36 security-relevant, of which 2 critical and 15 high. The active-repo filter is what makes this readable; without it the report is noise.
Read-only, without exception
This skill never mutates GitHub. No merging, no commenting, no review
requests, no label edits, no Dependency Dashboard checkbox ticking, no
gh api --method POST/PATCH/PUT/DELETE, no GraphQL mutation. Every script
here issues queries only.
If the user wants a PR applied, that is the dependency-updates skill's
job — name it and hand off. Do not add write capability to this skill, and do
not port the "optionally act" phase from the sibling github-pr-triage skill.
Scripts
| Script | Purpose |
|---|---|
scripts/active-repos.sh |
Repos in the org the user contributed to in the window |
scripts/fetch-renovate-prs.sh |
Open Renovate PRs, filtered to those repos |
scripts/enrich-renovate-prs.sh |
Per-PR body/files/checks + parse Renovate's update table |
scripts/advisory-lookup.sh |
Resolve GitHub Advisory Database records; attach severity/CVSS/EPSS |
scripts/classify-renovate-prs.sh |
Assign urgency tiers and sort |
The .sh files are orchestration only (argument parsing, gh calls,
parallelism). The heavy data transforms live as standalone jq programs in
scripts/jq/, one per stage, run with jq -f; shared shell helpers are in
scripts/lib.sh and the fixed file locations in scripts/paths.sh.
Never pass file paths
Run every command below exactly as written. The scripts hand JSON to each
other through fixed locations they compute themselves (scripts/paths.sh,
defaulting under ~/.cache/renovate-security-triage/) and print where they
wrote. Each accepts explicit paths for ad-hoc use, but the pipeline must not
supply them.
What ships with it
14 files 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.
- references/renovate-pr-anatomy.md 5.6 KB
- references/urgency-rubric.md 5.5 KB
- scripts/active-repos.sh 5.0 KB runs code
- scripts/advisory-lookup.sh 7.8 KB runs code
- scripts/classify-renovate-prs.sh 1.8 KB runs code
- scripts/enrich-renovate-prs.sh 2.1 KB runs code
- scripts/fetch-renovate-prs.sh 3.0 KB runs code
- scripts/jq/active-repos.jq 1.6 KB
- scripts/jq/advisory.jq 1.0 KB
- scripts/jq/classify.jq 3.8 KB
- scripts/jq/enrich.jq 5.2 KB
- scripts/jq/merge-advisories.jq 2.2 KB
- scripts/lib.sh 1.9 KB runs code
- scripts/paths.sh 1.8 KB runs code
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.
- 7d ago First seen · 347 lines · 157 tokens per session scan A 3659ed327471
renovate-security-triage is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 157 tokens to every session and 4,539 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…