claude-harness-workflow

claude-harness-workflow is a skill for Claude Code, Codex from NiroDu/claude-code-harness-kit. It costs 51 tokens per session (888 once invoked), scanned A, original, Apache-2.0.

A workflow for repositories that use claude-code-harness-kit, a set of files and commands for preserving coding-agent project state. It restores state, validates the setup, and uses repository artifacts as the source of truth.

In plain words
What is it for?
Initializing or validating the harness, rereading project state and decisions, and continuing work from the repository's documented artifacts.
Why use it?
It prevents a new or resumed session from guessing based only on old conversation context.

Skill for Claude CodeCodex

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 skills/nirodu/claude-code-harness-kit/claude-harness-workflow
Any agent
npx skills add NiroDu/claude-code-harness-kit --skill claude-harness-workflow
Clone the repo
git clone --depth 1 https://github.com/NiroDu/claude-code-harness-kit

Made for: Claude Code, Codex.

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 claude-harness-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirodu/claude-code-harness-kit/claude-harness-workflow.svg)](https://agentmods.dev/skills/nirodu/claude-code-harness-kit/claude-harness-workflow)
Your own site
<a href="https://agentmods.dev/skills/nirodu/claude-code-harness-kit/claude-harness-workflow"><img src="https://agentmods.dev/badge/skills/nirodu/claude-code-harness-kit/claude-harness-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 888 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00051 $0.00888
Opus 5 $0.00026 $0.00444
Sonnet 5 $0.00010 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured 5d ago against content hash 05c21a8a4af4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-harness-workflow 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.

extras/claude-skills/claude-harness-workflow/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Harness Workflow

Use this skill when the repo should be driven by claude-code-harness-kit, especially in these cases:

  • A new session starts in an empty repo and needs harness initialization before work begins.
  • A new session starts in an existing repo and should recover state before editing code.
  • A resumed session should stop relying on stale chat context and re-read the repo artifacts.
  • You want a short prompt such as "restore state and continue" but expect the full harness workflow.

Core rule

Do not begin implementation from chat context alone. Treat the repo artifacts as the source of truth:

  • CLAUDE.md
  • CLAUDE.harness.md when activated by CLAUDE.md
  • docs/harness-config.json
  • the configured state file from paths.stateFile
  • the configured memory file from paths.memoryFile
  • the configured decisions file from paths.decisionsFile
  • the active contract referenced by the current state

Workflow

  1. Decide whether the repo is empty or already has project files.
  2. If the repo does not appear to have a working harness yet, run claude-code-harness-kit init.
  3. Run claude-code-harness-kit validate-harness.
  4. If validation fails, repair or initialize the harness before continuing with feature work.
  5. Run claude-code-harness-kit check-state.
  6. Read the active harness artifacts and summarize:
    • current goal
    • current contract
    • blockers
    • next step
    • last verification result
  7. Only then continue with implementation or analysis.

Situation handling

New session in an empty repo

  • Initialize first with claude-code-harness-kit init.
  • Validate with claude-code-harness-kit validate-harness.
  • Summarize with claude-code-harness-kit check-state.
  • Tell the user what is missing if the initial state is still mostly blank, such as empty goal or verification commands.

New session in an existing repo

  • Do not assume the harness is already active.
  • Validate first.
  • If the repo has no harness, initialize it safely.
  • If the repo has an existing CLAUDE.md, preserve it and rely on the activation bridge workflow.
  • Recover state from the configured files before editing code.

Read the full file on GitHub · 109 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. 5d ago First seen · 109 lines · 51 tokens per session scan A 05c21a8a4af4

Subscribe to this mod's changes

claude-harness-workflow is a skill published in the GitHub repository NiroDu/claude-code-harness-kit (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 888 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens