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/qencode-corp/mcp/claude-mdgit clone --depth 1 https://github.com/Qencode-Corp/mcpWhat 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 | $0.03052 | $0.03052 |
| Opus 5 | $0.01526 | $0.01526 |
| Sonnet 5 | $0.00610 | $0.00610 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
mcp 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
qencode-mcp is the Resource Server (RS) half of the Qencode MCP integration. It exposes the Qencode Transcoding API as MCP tools, resources, and prompts over streamable HTTP, secured by OAuth 2.1 (the AS lives elsewhere, on auth.qencode.com / auth-qa.qencode.com). There is no stdio / static-QENCODE_API_KEY mode — the server only runs OAuth-protected over HTTP.
The connector is deployed in both environments: production https://mcp.qencode.com/mcp (Authorization Server https://auth.qencode.com) and QA https://mcp-qa.qencode.com/mcp (https://auth-qa.qencode.com). See docs/oauth-spec.md for the full AS↔RS contract (built by the portal team, consumed here), docs/testing.md for the test-layer overview, and docs/local-development.md for running the RS locally.
Common commands
# Install (editable, with dev extras)
uv venv && uv pip install -e ".[dev]"
# Lint
.venv/bin/ruff check src/ scripts/
# Run the server locally (needs every env var — see docs/local-development.md)
.venv/bin/qencode-mcp
# Regenerate the schema digest + index from the docs repo. Run this whenever
# transcoding.json changes upstream and commit the resulting files.
.venv/bin/python scripts/build_assets.py --docs-path /path/to/docs_getsby5
.venv/bin/python scripts/build_assets.py --check # CI guard for staleness
# Generate a fresh ES256 signing key for the §6.2 portal bridge
.venv/bin/python scripts/oauth_generate_signing_key.py
# Offline test suite (L1/L2/protocol/security; no network — see docs/testing.md)
.venv/bin/python -m pytest
# L3 integration against live QA (real portal + Qencode API; profile-aware launcher)
.venv/bin/python scripts/integration.py qa doctor # preflight: env / PEM / JWKS / seed
.venv/bin/python scripts/integration.py qa all # full suite (cheap + job-creating + e2e)
# L4 agent evals (LLM + local fake MCP; needs Claude Code CLI + CLAUDE_CODE_OAUTH_TOKEN)
.venv/bin/python scripts/l4.py eval --mode weekly --all
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.
- yesterday First seen · 110 lines · 3,052 tokens per session scan A 87f40d82d5d0
mcp CLAUDE.md is an instructions file published in the GitHub repository Qencode-Corp/mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 3,052 tokens to every session, about $0.0153 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
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.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.