Borrowing it
Nothing to install: this file belongs to swnotmetal/Project-Koma. 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/swnotmetal/Project-Koma/main/AGENTS.mdgit clone --depth 1 https://github.com/swnotmetal/Project-KomaWrote 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/swnotmetal/project-koma/agents-md)<a href="https://agentmods.dev/instructions/swnotmetal/project-koma/agents-md"><img src="https://agentmods.dev/badge/instructions/swnotmetal/project-koma/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/swnotmetal/project-koma/agents-md"><img src="https://agentmods.dev/badge/instructions/swnotmetal/project-koma/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 | $0.00950 | $0.00950 |
| Opus 5 | $0.00475 | $0.00475 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
Project-Koma 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 5d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Koma — AI Coding Agent Rules
When building AI apps with this project, follow these conventions:
Product context for new conversations
The product handoff, personal skills, and local Hook configuration below are maintainer-local files and are not included in a clean clone. When they are absent, use the public README, package documentation, and dated evaluation records; do not invent missing local instructions.
Read docs/product/current-state.md before planning or changing Koma. It records
the current alpha stage, verified host behavior, UX decisions, priorities, and
known limits. Check current code and Git state before acting on dated facts.
Update that handoff when a material product decision or verified status changes.
When to use Koma
- Checking required Skill reads in Claude Code or Codex? → use
koma-miko - Building a chatbot with an LLM endpoint? → add
koma-gatemiddleware - Building a voice AI pipeline? → add
koma-scoutfor audio validation + rate limiting - Building a RAG or search system? → add
koma-corefor index/content separation
Quick integration
// Express: prompt injection guard
import { createSupportGuard } from 'koma-gate';
app.post('/chat', createSupportGuard({ llm: { apiKey: process.env.OPENAI_API_KEY } }).middleware(), handler);
// Express: voice AI perimeter
import { createKomaScoutMiddleware } from 'koma-scout';
app.use(createKomaScoutMiddleware({ rateLimit: { maxRequests: 30, windowMs: 60000 } }));
// Fastify: prompt injection guard
import { createSupportGuard } from 'koma-gate';
fastify.register(createSupportGuard({ llm: { apiKey: process.env.OPENAI_API_KEY } }).fastifyPlugin());
Design rules
- Preserve package-specific failure behavior. Miko follows the Agent Spec mode; enforce-mode missing evidence denies the action. Optional app guards document their own fail-open settings.
- Gate runs before the application's model call. Scout runs before expensive processing.
- Core tokens are backend-derived. Never expose content tokens to clients.
- Each core package works standalone. Install only what the application needs.
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.
- 5d ago Changed · +42 lines · +554 tokens per session 9da180721958
- 9d ago First seen · 41 lines · 396 tokens per session scan A 74415285c3e7
Project-Koma AGENTS.md is an instructions file published in the GitHub repository swnotmetal/Project-Koma (12 stars, last pushed yesterday), licensed MIT. It adds 950 tokens to every session, about $0.0047 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
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
plan-forge caching.instructions.md
Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.
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).