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/phrase/phrase-mcp-server/agents-mdgit clone --depth 1 https://github.com/phrase/phrase-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 | $0.01037 | $0.01037 |
| Opus 5 | $0.00518 | $0.00518 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
phrase-mcp-server 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 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Guidance for AI agents (Claude, Copilot, etc.) contributing to this repository.
Commit Messages and PR Titles
All commit messages and PR titles must follow Conventional Commits. This is enforced by CI on pull requests.
Format: <type>: <description>
Common types:
feat— new feature or capabilityfix— bug fixdocs— documentation changes onlychore— maintenance, dependencies, configrefactor— code change that neither fixes a bug nor adds a featuretest— adding or updating tests
Examples:
feat: add readOnlyHint/destructiveHint annotations to all tools
fix: change download-target-file-async annotation to readOnlyHint
docs: add working examples section to README
chore: update Dependabot configuration
The PR title must also follow this format — the Semantic PR check will fail otherwise.
Tool Names
Tool names must be at most 64 characters. This is enforced by the Anthropic MCP Directory Policy and verified by the test suite.
Tool Annotations
Every tool registered with server.registerTool must declare an annotations field in its config object with three required fields. This is required for MCP directory submission.
Required annotation fields
-
title— a short human-readable label. Must be prefixed with[Strings],[TMS],[BQE], or[Connectors]to disambiguate between the Phrase products (e.g. both Strings and TMS have "Get Job", "List Projects", etc.). -
readOnlyHint: true— the tool does not modify operational user data. Use for:get_*/get-*— fetch a single resourcelist_*/list-*— list resourcessearch_*/search-*— search/query- Async polling helpers (
get_async_request,get_async_limits,list_pending_requests) - Async download triggers and file retrieval (
download_target_file_async,download_target_file_by_async_request,create_locale_download) — these initiate or retrieve exports but do not modify user data - Branch comparison (
compare_branch,get_branch_comparison) — read-only diff computation
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 · 1,037 tokens per session scan A 36d0c18994f4
phrase-mcp-server AGENTS.md is an instructions file published in the GitHub repository phrase/phrase-mcp-server (13 stars, last pushed 20d ago), licensed MIT. It adds 1,037 tokens to every session, about $0.0052 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
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
rosetta AGENTS.md
Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.
pharo-smalltalk-interop-mcp-server CLAUDE.md
Instructions for mumez/pharo-smalltalk-interop-mcp-server, covering claude.md, project overview, development setup, environment variables and common commands.