agentmods.dev

adaptive-harness: Instructions file for Claude Code

CLAUDE.md

adaptive-harness CLAUDE.md is an instructions file for Claude Code from SeongwoongCho/adaptive-harness. It costs 857 tokens per session, scanned A, original, MIT.

Repository instructions for adaptive-harness, including its Git branch workflow and release process. A branch is a separate line of development used to isolate changes.

In plain words
What is it for?
Use them when creating branches, naming work, opening pull requests, merging changes, or preparing releases.
Why use it?
They prevent agents from changing stable or shared branches directly and clarify where feature work and pull requests belong.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md.

This is SeongwoongCho/adaptive-harness's own configuration. It tells Claude Code how to work on adaptive-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adaptive-harness configures →

not rated 8repo 5mo ago A scan 857 tokens original MIT
View source ↗ SeongwoongCho/adaptive-harness
Reuse

Borrowing it

Nothing to install: this file belongs to SeongwoongCho/adaptive-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.

Copy the file
curl -O https://raw.githubusercontent.com/SeongwoongCho/adaptive-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SeongwoongCho/adaptive-harness

Made for: Claude Code.

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 adaptive-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seongwoongcho/adaptive-harness/claude-md/github.svg)](https://agentmods.dev/instructions/seongwoongcho/adaptive-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/seongwoongcho/adaptive-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/seongwoongcho/adaptive-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.

agentmods 80×15 button for adaptive-harness CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/seongwoongcho/adaptive-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/seongwoongcho/adaptive-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 857 This file is loaded in full into every session.
When invoked 857 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00857 $0.00857
Opus 5 $0.00428 $0.00428
Sonnet 5 $0.00171 $0.00171
Haiku 4.5 $0.00086 $0.00086

Measured 10d ago against content hash 61c15a88e57b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adaptive-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 10d 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

adaptive-harness — Project Instructions for AI Agents

Git Workflow

This project follows a structured branching strategy. All AI agents must follow these rules without exception.

Branch Structure

Branch Purpose
main Stable releases only. Contains tagged versions.
dev Integration branch. All feature work is merged here first.
feat/*, fix/*, docs/*, harness/*, fixture/*, chore/* Short-lived feature branches. Always branched from dev.

Rules for AI Agents

  1. Never commit directly to main or dev.
  2. Always create a new feature branch from dev before making any changes. 
    git checkout dev
git pull origin dev
git checkout -b feat/<short-description>
  3. All pull requests must target dev, not main.
  4. Branch naming convention: Use one of the following prefixes:
    • feat/ — new feature or capability
    • fix/ — bug fix
    • docs/ — documentation only
    • harness/ — harness definition changes
    • fixture/ — fixture or test data changes
    • chore/ — maintenance, version bumps, tooling

Release Flow

Automated Release (recommended)

Use the prepare-release workflow to automate version bumping and PR creation:

  1. Go to Actions → Prepare Release → Run workflow on GitHub.
  2. Enter the new version (e.g. 1.2.0) and click Run workflow.
  3. The workflow will:
    • Run scripts/bump_version.py <version> to update all version files.
    • Commit the version bump to dev.
    • Open a PR from dev → main with auto-generated release notes.
  4. Review and merge the PR.
  5. Tag the merge commit: git tag v1.2.0 && git push origin v1.2.0.
  6. The release workflow runs automatically on tag push, validates the version, generates the changelog, and creates a GitHub Release.
Manual Release

When a version is ready to release manually:

  1. Bump all version files in one command: 
    python3 scripts/bump_version.py <new_version>
  2. Commit, push, and open a PR from dev → main.
  3. Merge the PR, then tag the merge commit on main: 
    git tag v<new_version>
git push origin v<new_version>

Read the full file on GitHub · 88 lines

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. 10d ago First seen · 88 lines · 857 tokens per session scan A 61c15a88e57b

Subscribe to this mod's changes

adaptive-harness CLAUDE.md is an instructions file published in the GitHub repository SeongwoongCho/adaptive-harness (8 stars, last pushed 5mo ago), licensed MIT. It adds 857 tokens to every session, about $0.0043 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 2026-08-31.

Git and workflowReleasesa-b-testingai-agentai-orchestrationai-routingai-workflowautomation
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens