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/apify/apify-cli/claude-mdgit clone --depth 1 https://github.com/apify/apify-cliWhat 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 | $0.00708 | $0.00708 |
| Opus 5 | $0.00354 | $0.00354 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
apify-cli 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repository. Humans should read README.md and CONTRIBUTING.md first.
Entry points
apifyCLI —src/entrypoints/apify.tsactorCLI —src/entrypoints/actor.ts
Before you push
Run pnpm run lint && pnpm run format && pnpm run build && pnpm run test:local before pushing. Run pnpm run test:api too if you changed anything that touches the Apify API.
If you modified a command's flags, args, description, or added/removed a command, also run pnpm run update-docs and commit the regenerated docs/ output.
Code conventions
- Package manager: pnpm 10 (via Corepack). Do not use npm or yarn.
- Use
.jsimport specifiers for local files (e.g.import { foo } from './foo.js'). The.tssource resolves at build time. - Commands extend
ApifyCommandfromsrc/lib/command-framework/apify-command.ts. Follow the pattern of existing commands:static override name,static override description,static override flags/args, and anasync run()method. - New commands must be registered in
src/commands/_register.ts(or the parent_index.tsfor subcommands). - Do not add docstrings, comments, or type annotations to code you did not change. Keep diffs tight.
Install size
The CLI is installed globally by many users and in Actors, so keep the npm install footprint lean. Always look for opportunities to shrink it:
- Prefer Node.js built-ins over dependencies, and prefer dependencies already in the tree over new ones.
- Before adding a dependency, check what it drags in:
npm install <pkg>in an empty temp dir, thendu -sh node_modules. Mention the install-size impact in the PR description. - When touching code that uses a dependency, check whether the dependency is still pulling its weight — a single small helper from a large package is a candidate for replacement or removal.
- To measure the CLI's own footprint, run
node scripts/report-install-size.mjs— it packs the current tree and compares tarball, unpacked, and full-install sizes against the latest published version. The release workflows run it and embed the report in the GitHub release 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.
- 2d ago First seen · 47 lines · 708 tokens per session scan A f44548488921
apify-cli CLAUDE.md is an instructions file published in the GitHub repository apify/apify-cli (247 stars, last pushed 4d ago), licensed Apache-2.0. It adds 708 tokens to every session, about $0.0035 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 instructions, from other repositories
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
awesome-ai-apps AGENTS.md
Instructions for Arindam200/awesome-ai-apps, covering agents.md, repository overview, project categories, common development commands and running individual projects.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
maui collectionview-windows.instructions.md
Instructions for dotnet/maui, covering collectionview — windows (items/ handler), winui listview/itemsrepeater patterns, data source and change notifications, layout configuration and cross-platform consistency.
azure-sdk-for-net copilot-instructions.md
Instructions for Azure/azure-sdk-for-net, covering project overview, prerequisites, folder structure, azure generator and azure management generator.