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/ww-w-ai/bkit-claude-code/agents-mdgit clone --depth 1 https://github.com/ww-w-ai/bkit-claude-codeWrote 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/ww-w-ai/bkit-claude-code/agents-md)<a href="https://agentmods.dev/instructions/ww-w-ai/bkit-claude-code/agents-md"><img src="https://agentmods.dev/badge/instructions/ww-w-ai/bkit-claude-code/agents-md.svg" alt="Measured on agentmods" 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 | $0.00500 | $0.00500 |
| Opus 5 | $0.00250 | $0.00250 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
bkit-claude-code 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 4d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bkit Project Rules
Language Rules
Conversation
- Always respond in Korean (한국어) when communicating with the user.
Code & Documentation Language
-
English by default for ALL generated content:
- Code, comments, commit messages, PR descriptions
- README.md, CHANGELOG.md, and all non-docs/ markdown files
- Agent definitions (
agents/*.md), skill definitions (skills/*/SKILL.md) - Templates (
templates/*.md) - Config files, error messages, log messages
-
Korean exceptions (한국어 작성):
docs/directory and all subdirectories (docs/01-plan/,docs/02-design/,docs/03-analysis/,docs/04-report/)- 8-language auto-trigger keywords (EN, KO, JA, ZH, ES, FR, DE, IT) in agent/skill trigger lists
- bkit memory state descriptions in
.bkit/state/memory.json
Key Principle
bkit is a global service. Keep all public-facing and code-level content in English. Korean is only for internal planning docs (docs/) and developer communication.
Do NOT
- Do NOT translate existing English files to Korean (waste of tokens)
- Do NOT write docs/ files in English unless explicitly requested
- Do NOT mix languages within a single file (except trigger keyword lists)
Sprint Management (v2.1.13)
Sprint Management is a meta-container that groups one or more features under a
shared scope, budget, and timeline. Each sprint runs its own 8-phase lifecycle:
prd → plan → design → do → iterate → qa → report → archived.
When the user mentions "sprint", invoke bkit:sprint skill (/sprint <action>).
Sprint phases coexist with PDCA's 9-phase enum — both may track concurrently
(see docs/06-guide/sprint-migration.guide.md).
Trust Level scope (SPRINT_AUTORUN_SCOPE, L0–L4) controls auto-run boundaries.
At L4 Full-Auto, the orchestrator advances phases until any of 4 auto-pause
triggers fires (quality gate fail / iteration exhausted / budget exceeded /
phase timeout).
For deep-dive Korean guidance, see docs/06-guide/sprint-management.guide.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.
- 4d ago First seen · 45 lines · 500 tokens per session scan A 28f05cde3291
bkit-claude-code AGENTS.md is an instructions file published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 18d ago), licensed Apache-2.0. It adds 500 tokens to every session, about $0.0025 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
my-git AGENTS.md
Instructions for xirong/my-git, covering agents.md, 仓库结构, 改动后必须验证, 内容规则 and 禁止操作.
ai-native-sdlc AGENTS.md
Instructions for bashebr/ai-native-sdlc, covering agents.md, source of truth, validation and conventions.
robolearn CLAUDE.md
Claude Code instructions for mjunaidca/robolearn, covering claude code rules — reasoning-activated edition, 0. core identity: platform architect, i. before any task: stop and gather context, step 0: identify stakeholder & work type and step 1: read the platform context (mandatory).
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.