kirocc CLAUDE.md

kirocc CLAUDE.md is an instructions file for coding agents from d-kuro/kirocc. It costs 288 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Claude Code in kirocc, covering its Go codebase, commands, design principles, and maintenance rules.

In plain words
What is it for?
Building, testing, linting, running, and maintaining kirocc, including its end-to-end tests that use real Kiro API credentials.
Why use it?
They give the coding agent the project's working conventions and current commands, reducing incorrect changes and stale guidance.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/d-kuro/kirocc/claude-md
Clone the repo
git clone --depth 1 https://github.com/d-kuro/kirocc

Wrote 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.

agentmods badge for kirocc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/d-kuro/kirocc/claude-md.svg)](https://agentmods.dev/instructions/d-kuro/kirocc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/d-kuro/kirocc/claude-md"><img src="https://agentmods.dev/badge/instructions/d-kuro/kirocc/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 288 This file is loaded in full into every session.
When invoked 288 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00288 $0.00288
Opus 5 $0.00144 $0.00144
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 5d ago against content hash f1969f5b5a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kirocc 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 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.

CLAUDE.md · 48 lines

What it actually says

Agent Guidelines

Core Principles

  • Do NOT maintain backward compatibility unless explicitly requested. Break things boldly.
  • Keep this file under 20-30 lines of instructions.

Project Overview

Project type: CLI tool — local proxy server (Anthropic Messages API → Kiro backend) Primary language: Go


Commands

make build          # Build to dist/kirocc
make test           # go test -race ./...
make lint           # golangci-lint run
make run            # go run ./cmd/kirocc
make test-e2e       # E2E tests with real Kiro API (requires credentials)

Code Conventions

  • Follow the existing patterns in the codebase
  • Prefer explicit over clever
  • Delete dead code immediately

Maintenance Notes

Keep this file lean and current:

  1. Review regularly - stale instructions poison the agent's context
  2. CRITICAL: Keep total under 20-30 lines - move detailed docs to separate files and reference them
  3. Update commands immediately when workflows change
  4. Rewrite Architecture section when major architectural changes occur
  5. Delete anything the agent can infer from your code

Remember: Coding agents learn from your actual code. Only document what's truly non-obvious or critically important.

Changes

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.

  1. 5d ago First seen · 48 lines · 288 tokens per session scan A f1969f5b5a42

Subscribe to this mod's changes

kirocc CLAUDE.md is an instructions file published in the GitHub repository d-kuro/kirocc (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 288 tokens to every session, about $0.0014 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.