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/panyam/mcpkit/claude-mdgit clone --depth 1 https://github.com/panyam/mcpkitWhat 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 | $0.02257 | $0.02257 |
| Opus 5 | $0.01128 | $0.01128 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
mcpkit 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 3d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — MCPKit
Go library for building production-grade MCP servers and clients.
The agent SDK that used to sit above the protocol here now lives in its own repository, chakra. Nothing in this tree depends on it.
This file is a router. Detail lives beside the code it describes. See Where knowledge lives below before adding anything here.
Quick Commands
make is the supported runner and the only one CI uses. Justfiles mirroring these names exist but
are an experiment; make is authoritative when they disagree.
make test # Core tests (core/server/client/testutil)
make test-auth # ext/auth sub-module
make test-ui # ext/ui sub-module
make test-e2e # E2E tests (auth + apps)
make test-examples # examples/ orchestrator
make testall # Everything (9 stages, 21 sub-stages) + Keycloak + HTML report
make audit # govulncheck + gosec + gitleaks + race
make tidy-all # Required after touching core/ imports
make tag-push V=vX.Y.Z # Tag root + all sub-modules and push (RELEASING.md; pre-release is vX.Y.Z-bN)
Conformance targets (testconf, testconf-client, testconf-tasks-v2, testconf-mrtr,
testconf-skills, testconf-stateless, testconf-upstream-audit, refresh-conformance,
check-conformance-stale, …) are orchestrated in conformance/Makefile, which also documents each
suite's MCPCONFORMANCE_*_PATH. See conformance/NOTES.md for how they are wired and which
upstream changes to watch.
Package Layout
| Package | Docs |
|---|---|
core/ — Protocol types, typed contexts, session APIs |
core/README.md, core/CONSTRAINTS.md |
server/ — Server, transports, middleware, v1 tasks (frozen) |
server/README.md, server/CONSTRAINTS.md, server/NOTES.md |
client/ — Client, transports, reconnection, auth retry |
client/README.md, client/CONSTRAINTS.md |
ext/auth/ — JWT, PRM, OAuth |
ext/auth/docs/DESIGN.md, ext/auth/NOTES.md |
ext/tasks/ — SEP-2663 v2 tasks extension |
ext/tasks/README.md |
ext/skills/ — SEP-2640 skills (data-only, enforced) |
ext/skills/NOTES.md |
ext/ui/ — MCP Apps, Bridge JS, AppHost, ServerRegistry |
docs/APPS_DESIGN.md, docs/APPS_HOST.md, ext/ui/NOTES.md |
ext/otel/ — SEP-414 OpenTelemetry adapter |
ext/otel/README.md, docs/SEP_414_OTEL.md |
experimental/ext/events/ — MCP Events protocol |
experimental/ext/events/README.md, experimental/ext/events/NOTES.md |
experimental/ext/agents/ — Server-declared agent discovery (pre-SEP) |
experimental/ext/agents/README.md, experimental/ext/agents/NOTES.md |
experimental/ext/protogen/ — Proto → MCP codegen |
experimental/ext/protogen/docs/DESIGN.md |
conformance/ — Suite orchestration + audits |
conformance/NOTES.md |
examples/ — Working examples |
examples/README.md, examples/CONVENTIONS.md, examples/NOTES.md |
testutil/, tests/e2e/, tests/keycloak/ — Helpers and integration tests |
tests/e2e/apps/README.md |
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.
- 3d ago First seen · 140 lines · 2,257 tokens per session scan A d321e98e0d82
mcpkit CLAUDE.md is an instructions file published in the GitHub repository panyam/mcpkit (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,257 tokens to every session, about $0.0113 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
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).
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.
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.