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-mcp-server/agents-mdgit clone --depth 1 https://github.com/apify/apify-mcp-serverWhat 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 | $0.02347 | $0.02347 |
| Opus 5 | $0.01174 | $0.01174 |
| Sonnet 5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
apify-mcp-server AGENTS.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
When the user says "test with mcpc", **use mcpc** — do not invent a substitute (no curl, no ad-hoc Node/Python scripts, no unit tests in place of an e2e probe). Use the **apify CLI** (`apify datasets`, `apify key-value-s How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apify MCP server
TypeScript, ES modules. Runs in two modes: stdio (local CLI clients, stdio.ts) and HTTP Streamable (dev_server.ts).
Before implementing: work from an issue that is assigned or explicitly agreed. An open issue is not an invitation — many are stale or unrefined, and the fix isn't settled. If nobody asked for this change, open an issue instead of a PR (docs fixes excepted). Disclose AI use in the PR; never add a model as co-author. See CONTRIBUTING.md.
Communication style — MANDATORY
This applies to ALL written output: code comments, commit messages, PR descriptions, issue specs
- Plain language, no fluff. Say what you mean in the fewest words. No filler phrases, no motivational preambles, no "this will improve the developer experience."
Scope discipline
- Minimal. Implement only what's explicitly requested. No speculative features, no hypothetical future-proofing — solve the current problem, not imagined ones.
- One thing per change. Bug fix fixes only the bug — no cleanup, no renames, no drive-by refactors. Mention unrelated issues; don't fix them.
- Test first for bug fixes. Write a failing test that reproduces the bug, confirm it fails, then fix.
- Refactoring is a separate PR. If a feature needs refactoring, land the refactor first, then the feature. Never mix.
- Fix by adjusting, not adding. Prefer a 1-line fix over a 10-line fix. Prefer adjusting existing code over adding new branches. Search for existing helpers and patterns that already handle similar cases. Ask: "Am I adding code, or fixing the code that's already there?"
- Self-review your diff. Before declaring done, review: Is this the minimal fix? Am I reusing existing patterns? Did I leave any debug artifacts?
Git: branch names, commits, PR titles
Conventional Commits for all three. Branch: type/short-desc (e.g. fix/connection-timeout). Commit/PR title: type: Description (e.g. fix: Handle connection errors). Types: feat, fix, chore, refactor, docs, test. Append ! for breaking changes. PR title ≤70 chars.
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 · 96 lines · 2,347 tokens per session scan A 58747f84ade5
apify-mcp-server AGENTS.md is an instructions file published in the GitHub repository apify/apify-mcp-server (5,636 stars, last pushed yesterday), licensed MIT. It adds 2,347 tokens to every session, about $0.0117 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
omnigent copilot-instructions.md
Copilot instructions for omnigent-ai/omnigent, covering copilot code review instructions, e2e test requirement, backend test coverage and frontend test coverage.
AutoAgents AGENTS.md
Instructions for liquidos-ai/AutoAgents, covering autoagents repository guidelines, project structure & module organization, code quality, naming conventions and error handling.
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).