Borrowing it
Nothing to install: this file belongs to chrbailey/promptspeak-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrbailey/promptspeak-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrbailey/promptspeak-mcp-serverWrote 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/chrbailey/promptspeak-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/chrbailey/promptspeak-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/chrbailey/promptspeak-mcp-server/claude-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 5.1 | $0.01253 | $0.01253 |
| Opus 5 | $0.00626 | $0.00626 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
promptspeak-mcp-server 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptSpeak - Claude Instructions
Overview
Pre-execution governance layer for AI agents. Intercepts MCP tool calls, validates against deterministic rules, blocks or holds risky operations for human approval. Validation latency: 0.164ms avg (P95: 0.368ms).
v0.4.1 — 886 tests, 56 MCP tools, MIT licensed, published as @chrbailey/promptspeak-mcp-server.
Execution model: STEP 6 of the pipeline runs a pluggable
ToolExecutorwhen registered (gatekeeper.setExecutor), otherwise it simulates (safe default — unchanged behavior). For async tools,gatekeeper.executeAsync()awaits anAsyncToolExecutor(setAsyncExecutor) through the same pipeline;ps_executeuses it. Pre-checks (STEP 1–5) and post-audit (STEP 7–9) are shared viaprepareExecution/finalizeExecutionso the sync and async paths stay identical. Drift embeddings are content-aware via theEmbeddingProviderseam (deterministic-local by default; inject a real model withsetEmbeddingProvider). The handshake supports HMAC-SHA256 challenge–response (PROMPTSPEAK_HANDSHAKE_SECRET).
HTTPS live at https://promptspeak.admin-as-a-service.com/mcp (Cloudflare Tunnel → Mac Mini).
Safety annotations on all 56 tools. Streamable HTTP transport. Connectors submission: all requirements met, form submitted 2026-03-21.
General Principles
- Prefer simplicity over cleverness. Before building new infrastructure or multi-layer abstractions, ask whether updating existing files (CLAUDE.md, MEMORY.md) or a simpler approach would suffice. The codebase was cut from 82K to 16K lines by following this principle.
- Always produce complete output. Never return "No response requested" or truncated results. If output will be long, break it into clearly labeled parts and continue without being asked.
Pipeline Execution Rules
- Validate phase output before proceeding. Each phase must produce non-empty output before passing to the next phase. If upstream data is None/empty, halt and report the failure clearly rather than silently continuing with training knowledge.
- Confirm the target before each phase. When generating dossiers or research reports, always confirm the target company/entity name before each phase and never mix up targets mid-pipeline.
- Verify tool access before starting. Before web research tasks, verify that WebSearch and WebFetch tool permissions are granted. If denied, immediately inform the user rather than repeatedly attempting and failing silently.
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.
- 8d ago First seen · 80 lines · 1,253 tokens per session scan A c855c3087e74
promptspeak-mcp-server CLAUDE.md is an instructions file published in the GitHub repository chrbailey/promptspeak-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,253 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.