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 Sagargupta16/claude-skills --skill renovate-triagegit clone --depth 1 https://github.com/Sagargupta16/claude-skillsWrote 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/sagargupta16/claude-skills/renovate-triage)<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/renovate-triage"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/renovate-triage/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/sagargupta16/claude-skills/renovate-triage"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/renovate-triage.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 | $0.00062 | $0.00651 |
| Opus 5.5 | $0.00025 | $0.00260 |
| Sonnet 5.5 | $0.00012 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
renovate-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 2mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
renovate-triage
Live data
- Open Renovate PRs authored by
app/renovateon your repos: !gh search prs --author app/renovate --state open --json repository,title,number,url --limit 100 2>/dev/null || echo "gh unavailable or not authenticated"
When to activate
- User says "renovate triage", "review dep PRs", "monthly deps", "batch deps".
- It's the 1st of the month and deps are grouped monthly.
Skip if: the user is asking about a single specific PR (use a PR-review skill instead), or if Renovate isn't configured on their repos.
Steps
- Use the live PR list above. Do not re-fetch.
- Group by repo. One repo's PRs often share the same grouping rule.
- For each PR, fetch merge state and CI:
gh api repos/{owner}/{repo}/pulls/{num} --jq '{mergeable, mergeStateStatus, title, labels}'gh pr checks <url>
- Classify each PR:
- Merge -- CI green, patch or minor bump, library is stable and well-adopted, no flags in the repo's Renovate config.
- Close -- superseded by a newer PR, wrong repo, duplicate, or abandoned.
- Defer -- major version bump, known breaking change, CI red that needs investigation, or a library that the repo pins deliberately.
- Output a table grouped by repo with recommended action per PR.
- Do not merge automatically. Present the plan; the user approves.
- After approval, merge in order, one repo at a time, verifying CI between merges (not in parallel).
Rules
- Never merge a Renovate PR with unresolved security findings on the PR or the repo.
@types/*-only bumps can silently break builds -- always check CI is green before merging, not just "mergeable".- Major bumps always defer. React 18 -> 19, Next 14 -> 15, Node 20 -> 22, etc. These are planned work, not routine hygiene.
- Close old superseded PRs before merging the latest one in a grouped series -- otherwise Renovate may reopen them.
Output
| Repo | PR | Bump | CI | Action | Notes |
|---|---|---|---|---|---|
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.
- 2mo ago First seen · 51 lines · 62 tokens per session scan A 956d8bf55524
renovate-triage is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 651 once invoked, about $0.0002 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.
renovate-triage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| renovate-triageSagargupta16/claude-skills | Skill | 5 | yesterday | MIT | A | 62 | Claude Code |
| changelog-summarizingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 106 | Claude Code |
| plugin-updatingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 102 | Claude Code |
| commit-message-writingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 160 | Claude Code |
| morning-briefmelodic-software/claude-code-plugins | Skill | 30 | today | MIT | A | 152 | Claude Code |
| realign-file-namesmelodic-software/claude-code-plugins | Skill | 30 | today | MIT | A | 114 | Claude Code |
| applymelodic-software/claude-code-plugins | Skill | 30 | today | MIT | A | 109 | Claude Code |