Borrowing it
Nothing to install: this file belongs to kyungseo/ai-workflow-harness. 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/kyungseo/ai-workflow-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/kyungseo/ai-workflow-harnessWrote 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/kyungseo/ai-workflow-harness/claude-md)<a href="https://agentmods.dev/instructions/kyungseo/ai-workflow-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/kyungseo/ai-workflow-harness/claude-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/kyungseo/ai-workflow-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/kyungseo/ai-workflow-harness/claude-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 | $0.00355 | $0.00355 |
| Opus 5 | $0.00178 | $0.00178 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
ai-workflow-harness 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 9d 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.
What it actually says
CLAUDE.md
Claude Code entry point for this repository.
Keep this file thin. Global behavior principles live in docs/BEHAVIOR-PRINCIPLES.md. Shared operating rules live in docs/AGENT-WORKFLOW.md.
@docs/BEHAVIOR-PRINCIPLES.md @docs/AGENT-WORKFLOW.md
Entry Contract
MUST:
- Treat this file and
AGENTS.mdas equal tool-specific entry points. Supported tools are Claude Code / Codex / Antigravity (Gemini-based) / Cursor. Antigravity has no dedicated entry file: it auto-loads rootAGENTS.mdand consumes.agents/skills/(the Codex surface). - Follow
docs/BEHAVIOR-PRINCIPLES.mdfor global behavioral principles that apply to all tasks. - Follow
docs/AGENT-WORKFLOW.mdfor common workflow, context routing, status rules, and validation defaults. - Read
docs/STATUS.mdcurrent sections before choosing or continuing work. - Do not check
docs/BOOTSTRAP.mdjust because it exists; use it only whendocs/STATUS.mdNext Actions explicitly points to scaffold bootstrap/onboarding work. - Use
.claude/commands/for repeated Claude Code workflows when available. - Do not read
.claude/commands/*.mdat session start; load a command file only when that workflow is explicitly invoked or clearly relevant. - Follow
docs/AGENT-WORKFLOW.mdApproval Matrix before execution, scope expansion, state changes, and every commit.
NEVER:
- Duplicate shared rules here.
- Bypass
docs/STATUS.mdor the Approval Matrix.
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.
- 9d ago First seen · 26 lines · 355 tokens per session scan A a13b5689f046
ai-workflow-harness CLAUDE.md is an instructions file published in the GitHub repository kyungseo/ai-workflow-harness (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 355 tokens to every session, about $0.0018 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
multiagent-template copilot-instructions.md
Instructions for Neftedollar/multiagent-template, covering workspace structure, how to work in this repo, multi-agent pipeline, orchestrator role and escalate to human only for.
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).
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).
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.