Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/AGENTS.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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/moberghr/mtk-agent-toolkit/agents-md)<a href="https://agentmods.dev/instructions/moberghr/mtk-agent-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/moberghr/mtk-agent-toolkit/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/moberghr/mtk-agent-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/moberghr/mtk-agent-toolkit/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02161 | $0.02161 |
| Opus 5.5 | $0.00864 | $0.00864 |
| Sonnet 5.5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
mtk-agent-toolkit 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 7d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-helpers — MTK Standards
Canonical instructions for every AI coding agent working in this repo — Claude Code, Codex CLI, Cursor, Copilot, Windsurf, OpenCode and anything else that reads
AGENTS.md.CLAUDE.mdis a shim that imports this file; the tool-specific mirrors under.github/and.windsurf/point here.Version history and per-release notes: see CHANGELOG.md. (Kept out of this file so the always-loaded prefix stays prompt-cache-stable across releases.)
This file +
.claude/rules/are the source of truth for AI agents. Detailed standards live in.claude/rules/. Reference docs live in.claude/references/(shared) and per-stack subdirectories of it.
Skill Routing
| What you need | Command | When |
|---|---|---|
| First-time repo setup | /mtk-setup |
Bootstrap — detects tech stack, pulls guidelines, generates AGENTS.md (plus the CLAUDE.md shim) and the architecture-principles reference |
| Re-run audit | /mtk-setup --audit |
Refresh the generated architecture-principles reference after architectural change |
| Merge multi-repo audits | /mtk-setup --merge |
Unify per-repo audits in .claude/references/audits/ into a team-wide doc |
| Everything else | /mtk <description> |
Natural language — routes to fix / batch-fix / implement / pre-commit-review / repo-health / instructions / mtk-doctor |
| Run a known workflow directly | /mtk:implement, /mtk:fix or /mtk:batch-fix |
Skip the router when you already know the workflow — same skill the router would load |
| Periodic readiness check | /mtk repo-health or bash scripts/repo-health-score.sh |
9-asset action checklist + PR review mining (last 10 merged PRs) |
| Validate toolkit | bash scripts/validate-toolkit.sh |
Before every commit — structural check of manifest, plugin.json, and skill anatomy |
| Install health check | /mtk-doctor |
PASS/WARN/FAIL diagnostics across core files, components, hooks, active config and environment fit; --json for CI, --fix for safe auto-repairs, --usage for raw usage counts |
| Promote a lesson | /lessons promote |
Promote a rule from Claude Code native memory to team-wide tasks/lessons.md; optionally open a validated contribute-back PR to the toolkit (/promote-lesson is a one-release alias) |
| Mine lessons from past sessions | /lessons mine |
Sweep recent session transcripts for durable lesson/memory candidates (reject-by-default rubric, suggest-only) |
| Tune MTK behaviour (hooks, rigor, budgets, thresholds) | MTK_* environment variables |
Full table of every knob, its default and effect: .claude/references/env-knobs.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.
- 7d ago Changed · +51 tokens per session c523a32a4bd3
- 8d ago Changed · +1 lines · +73 tokens per session 9fd93667e040
- 16d ago Changed · +47 tokens per session 36b74896be22
- 1mo ago Changed · -48 lines · -424 tokens per session ceef070357f4
- 2mo ago First seen · 168 lines · 2,414 tokens per session scan A ea2d5443f4bd
mtk-agent-toolkit AGENTS.md is an instructions file published in the GitHub repository moberghr/mtk-agent-toolkit (9 stars, last pushed 8d ago), licensed MIT. It adds 2,161 tokens to every session, about $0.0086 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.