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/thecombatwombat/replicant-mcp/agents-mdgit clone --depth 1 https://github.com/thecombatwombat/replicant-mcpWrote 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/instructions/thecombatwombat/replicant-mcp/agents-md)<a href="https://agentmods.dev/instructions/thecombatwombat/replicant-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thecombatwombat/replicant-mcp/agents-md.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 | $0.00524 | $0.00524 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
replicant-mcp AGENTS.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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
replicant-mcp
Android MCP server for AI-assisted Android development. Published to npm as replicant-mcp.
Decision Log
Check DECISIONS.md before making architectural or workflow choices. Add entries for significant decisions.
Issue Tracking
- Backlog lives in Linear. Never create backlog items, epics, or feature requests in beads.
- Beads is working memory only. Use it for cross-session tasks you are actively working on — 3-5 items max. Close immediately when done. Do not accumulate issues.
- Scope all Linear issues to the replicant-mcp project only.
MCP Resources
- Context7: Use for library/API docs, code examples, and configuration guidance.
- Linear: Use for backlog and roadmap (see Issue Tracking above).
Code Health
- File limit: 500 lines. Function limit: 80 lines. CLI command builders (
src/cli/) excluded. - Tool operations are separate named functions; main handler dispatches.
- No module-level mutable state. Use ServerContext.
- Use ReplicantError. Never swallow errors silently.
Testing
- Coverage enforced via thresholds in
vitest.config.ts. Runnpm run test:coveragebefore PR. - Test before implement. Unit tests in
tests/<category>/, integration intests/integration/. - Cover happy paths, error cases, edge cases, retries, boundaries, and mock external deps.
Privacy Policy
PRIVACY.md documents what data replicant-mcp accesses and where it goes. Review and update it when:
- Adding new data sources (new ADB data types, network traffic, file system access)
- Adding any external network calls, telemetry, or analytics
- Changing data persistence behavior (caching, logging to disk)
- Adding new third-party dependencies that process user data
- Changing how data flows to the AI assistant
When in doubt, flag the PR with a comment noting the privacy policy may need review.
PR & Branches
- Never push directly to master. No exceptions, no matter how small the change. Always create a branch and use
/create-pr. - Branch format:
<prefix>/<short-description> - Prefixes:
feature/,fix/,docs/,refactor/,chore/,trivial/ - Monitor for Greptile review. Wait for human approval before merging.
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.
- 5d ago First seen · 54 lines · 524 tokens per session scan A d822a2e8b1d7
replicant-mcp AGENTS.md is an instructions file published in the GitHub repository thecombatwombat/replicant-mcp (16 stars, last pushed 1mo ago), licensed MIT. It adds 524 tokens to every session, about $0.0026 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
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.