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 FlorianBruniaux/claude-code-plugins --skill routines-discovergit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/routines-discover)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/routines-discover"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/routines-discover.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 | $0.00039 | $0.00963 |
| Opus 5 | $0.00019 | $0.00481 |
| Sonnet 5 | $0.00008 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade B, and why
routines-discover scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Any monitoring, deploy, or ops configuration you find If MCP connectors are configured in `.claude/settings.json`, note which external services are connected. How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routines Use Case Discovery
Analyzes this codebase and surfaces actionable Routine candidates across the three trigger types.
Usage: /routines-discover - no arguments needed. Run it in the root of any project.
What Are Routines
A Routine is an autonomous Claude Code session running on Anthropic-managed cloud infrastructure, triggered in three ways:
| Trigger | How it fires |
|---|---|
| Schedule | Recurring cron cadence (min 1 hour) |
| API | HTTP POST to a per-routine endpoint with bearer token |
| GitHub events | Repository events: PR opened/merged, push, issue, workflow run, etc. |
Each run clones a fresh copy of the GitHub repository, runs a full Claude Code session with configured MCP connectors (Slack, Linear, GitHub, Google Drive…), and can create branches, open PRs, post messages, and call external APIs. No local machine required.
Daily limits: Pro 5/day · Max 15/day · Team/Enterprise 25/day.
Instructions
Step 1: Read the codebase
Before generating any output, silently read:
README.mdorCLAUDE.mdto understand the project purpose and stackpackage.json,Cargo.toml,pyproject.toml, or equivalent for dependencies.github/workflows/to understand existing CI/CD automation- Any monitoring, deploy, or ops configuration you find
If MCP connectors are configured in .claude/settings.json, note which external services are connected.
Step 2: Analyze against five dimensions
For each dimension, think concretely about this specific project before writing anything.
1. Scheduled maintenance What recurring work currently requires a human to run manually or remember to do? Think: dependency audits, stale issue/PR triage, test flakiness reports, coverage drift, TODO comment tracking, dead code detection, daily or weekly summaries.
2. Event-driven reactions What should happen automatically when a PR is opened, merged, or closed, but doesn't today because no one gets to it? Think: review checklists, changelog updates, cross-repo sync, Slack notifications with context, label enforcement, docs updates on API changes.
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 · 107 lines · 39 tokens per session scan B ea2a0bc39911
routines-discover is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 963 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…