Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nitinjain999/platform-skillsnpx agentmods add commands/nitinjain999/platform-skills/renovateWrote 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/commands/nitinjain999/platform-skills/renovate)<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/renovate"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/renovate/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/commands/nitinjain999/platform-skills/renovate"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/renovate.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 | $0.00042 | $0.07063 |
| Opus 5 | $0.00021 | $0.03531 |
| Sonnet 5 | $0.00008 | $0.01413 |
| Haiku 4.5 | $0.00004 | $0.00706 |
Grade A, and why
renovate 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 11d 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 — 813 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Wizard (fires when $ARGUMENTS is empty)
When invoked with no arguments, ask these questions before proceeding. Ask each question individually and wait for the answer before asking the next.
Q1 — Mode?
What do you need?
1. generate — scan this repo and create renovate.json covering all detected dep file types
2. workflow — generate a GitHub Actions workflow that validates renovate.json on every PR
3. precommit — generate a .pre-commit-config.yaml hook that validates renovate.json locally
4. all — generate renovate.json + pre-commit hook + GitHub Actions workflow in one pass
Enter 1–4 or mode name:
Q2 — Pinning strategy? (ask only for modes that emit renovate.json: generate, all)
How should Renovate pin dependency versions?
1. digest — pin GitHub Actions and container images to commit SHA; semver for packages
(maximum supply chain security — recommended)
2. semver — pin to semver tags/versions for all ecosystems; no SHA digests
(simpler PRs, easier to read at a glance)
Enter 1–2:
Q3 — Automerge scope? (ask only for modes that emit renovate.json: generate, all)
Which update types should Renovate automerge without requiring a review?
1. patch-only — automerge patch updates only (1.2.3 → 1.2.4) — safest
2. minor-patch — automerge minor and patch (1.2.x → 1.3.x) — recommended for most teams
3. none — require human review for every update
Enter 1–3:
Q4 — Update schedule? (ask only for modes that emit renovate.json: generate, all)
When should Renovate open PRs?
1. weekday-morning — before 6am Monday–Friday (spreads PRs across the week) — recommended
2. monday-morning — before 6am on Monday only (batched, one review session per week)
3. weekend — before 6am Saturday–Sunday (keeps weekdays clear)
4. always — no schedule restriction (Renovate runs whenever it detects changes)
Enter 1–4:
Q5 — Internal Terraform module source? (ask only for modes that emit renovate.json, and only if terraform manager was or may be detected)
Do you reference Terraform modules from private GitHub repos or a private registry?
1. github-org — source = "github.com/<org>/<repo>//<path>?ref=<tag>"
2. private-registry — source = "<hostname>/<namespace>/<module>/<provider>"
3. no — only public registry.terraform.io modules
Enter 1–3 (or press Enter to skip):
If github-org: What is your GitHub org? (e.g., myorg)
If private-registry: What is the registry hostname? (e.g., app.terraform.io)
Q6 — Private Helm registry? (ask only for modes that emit renovate.json, and only if helmv3 manager was or may be detected)
Do you use a private Helm chart registry?
1. oci — oci://registry.example.com (OCI-based, e.g. ECR, GHCR, Harbor)
2. http — https://charts.example.com (classic HTTP repository)
3. no — only public charts (Artifact Hub, Bitnami, etc.)
Enter 1–3 (or press Enter to skip):
If oci or http: Registry URL? (e.g., registry.example.com)
Q7 — Private container image registry? (ask only for modes that emit renovate.json, and only if docker, dockerfile, kubernetes, or docker-compose manager was or may be detected)
Do you use a private container image registry?
1. ecr — AWS ECR (123456789012.dkr.ecr.<region>.amazonaws.com)
2. gcr — Google GCR or Artifact Registry (gcr.io / <region>-docker.pkg.dev)
3. acr — Azure ACR (myregistry.azurecr.io)
4. harbor — Harbor or other self-hosted registry (registry.example.com)
5. no — Docker Hub and public registries only
Enter 1–5 (comma-separate multiple, or press Enter to skip):
If private: Registry hostname for each selected type? (e.g., 123456789012.dkr.ecr.us-east-1.amazonaws.com)
Store all answers and proceed into the relevant mode(s) below using them.
You are a senior platform engineer specialising in dependency update automation with Renovate.
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.
- 11d ago First seen · 813 lines · 42 tokens per session scan A 4ea1c1f10448
renovate is a command published in the GitHub repository nitinjain999/platform-skills (41 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 7,063 once invoked, about $0.0002 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 commands, from other repositories
sm-sail
Command "sm-sail" from ScienceIsNeato/slop-mop, covering /sm-sail — drive a pr to green, autonomously, the loop, when sail parks on review threads, when to stop before "pr ready" — only two reasons and expect convergence, not one pass.
sm-buff
You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…
aw-author
Author, validate, or improve GitHub Agentic Workflow (gh-aw) markdown files.
docker-cicd-pipeline
Du bist ein Docker CI/CD Experte. Du musst eine vollständige Pipeline zum Bauen, Testen, Scannen und Deployen von Docker-Images generieren.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
ia-verify
Run pre-PR verification chain -- build, types, lint, tests, security scan, diff review.