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 instructions/whenlabs-org/when/claude-mdgit clone --depth 1 https://github.com/WhenLabs-org/whenWhat 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 | $0.00951 | $0.00951 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
when CLAUDE.md 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.
This is a copy
92% identical to when AGENTS.md — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: @whenlabs/when
The WhenLabs developer toolkit — 6 tools, one install
Tech Stack
- Language: TypeScript 5.7
- Testing: Vitest 3.0
- Package Manager: pnpm
- Monorepo: pnpm-workspaces
- Deployment: Docker
- CI/CD: GitHub Actions
- Bundler: tsup 8.0
Docker
Dockerfile Best Practices
- Use multi-stage builds: a
builderstage for compilation/dependencies and a slimrunnerstage for the final image - Copy dependency manifests first (
package.json,package-lock.json) and install before copying source — leverages layer caching - Use specific base image tags (e.g.,
node:20-alpine) — never uselatestin production - Run the application as a non-root user:
RUN adduser --disabled-password appuser && USER appuser
.dockerignore
- Always include a
.dockerignorefile to exclude:node_modules,.git,.env, build artifacts, test files - This reduces build context size and prevents secrets from leaking into the image
Layer Caching
- Order Dockerfile instructions from least to most frequently changing for optimal caching
- Pin dependency versions in lock files so the install layer is cached until dependencies actually change
- Use
COPY --from=builderto copy only build artifacts into the final stage
Security
- Never store secrets in the image — use runtime environment variables or secret management
- Scan images for vulnerabilities:
docker scout cvesor integrate Trivy/Snyk in CI - Keep images minimal — use
alpineordistrolessbase images to reduce attack surface - Set
HEALTHCHECKinstructions for container orchestrators to monitor application health
Compose
- Use
docker-compose.ymlfor local development with all services (DB, cache, app) - Mount source code as a volume for hot-reloading in development
- Use
depends_onwith health checks to control startup order
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 · 98 lines · 951 tokens per session scan A bdf222d3a43b
when CLAUDE.md is an instructions file published in the GitHub repository WhenLabs-org/when (3 stars, last pushed 8d ago), licensed MIT. It adds 951 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to when AGENTS.md, differing in 22 lines, and is treated as a copy.
Other instructions, from other repositories
syllago CLAUDE.md
Instructions for OpenScribbler/syllago, covering syllago, build and test, key conventions, architectural decisions and testing requirements.
syllago AGENTS.md
Instructions for OpenScribbler/syllago, covering agent instructions, landing the plane (session completion), bv + br (graph-aware triage), entry point and workflow.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
com-example-config-AsyncTestConfig
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.