geniro-claude-harness: Instructions file for Claude Code

CLAUDE.md

geniro-claude-harness CLAUDE.md is an instructions file for Claude Code from geniro-io/geniro-claude-harness. It costs 2,389 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for geniro-io/geniro-claude-harness, a code-development setup used by Claude Code and Cursor. It defines how skills are routed, how read-only work is handled, and how project state files are treated.

In plain words
What is it for?
Guiding planning, implementation, review, debugging, investigation, and pull-request comment resolution in the geniro project.
Why use it?
It keeps the two supported coding environments aligned and clarifies which workflows may change source code.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; names the NotebookEdit tool; mentions Claude Code.

This is geniro-io/geniro-claude-harness's own configuration. It tells Claude Code how to work on geniro-claude-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 geniro-claude-harness configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to geniro-io/geniro-claude-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/geniro-io/geniro-claude-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/geniro-io/geniro-claude-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 geniro-claude-harness CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/geniro-io/geniro-claude-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/geniro-io/geniro-claude-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,389 This file is loaded in full into every session.
When invoked 2,389 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 $0.02389 $0.02389
Opus 5 $0.01195 $0.01195
Sonnet 5 $0.00478 $0.00478
Haiku 4.5 $0.00239 $0.00239

Measured 4d ago against content hash 97d7e5554c86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

geniro-claude-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 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.

CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Geniro Plugin

One skills/ directory ships to two runtimes, Claude Code and Cursor.

Skill routing

Each skill's frontmatter description is the routing surface, and Claude Code already loads them at discovery — don't restate them here. Three things those descriptions don't carry:

  • /geniro:implement and /geniro:resolve are the skills that ship code. /geniro:plan, /geniro:review, and /geniro:debug are producers: they end at a spec.md and/or a handoff file that /geniro:implement consumes and applies. /geniro:resolve owns its own loop end to end — it decides which PR comments are worth doing, applies those fixes, and closes the threads.
  • Read-only means production source unchanged at exit — not an empty tool surface. /geniro:review, /geniro:debug, and /geniro:investigate end every run with production source as they found it, and an elevated-effort or workflow run does not relax that; /geniro:debug alone gets there by reverting rather than by abstaining — its verification escape hatch edits production source when a chain cannot be mocked, then reverts every touched path before escalating. All three hold the rule as a prose contract, not a tool-level block: a skill's allowed-tools only pre-approves listed tools, so omitting Write/Edit skips the permission prompt for them but never blocks the call (skills/_shared/reporter-boundary.md §1). /geniro:refactor does edit production source, but never ships: the working-tree diff is its deliverable.
  • Skills have been deleted. A name that doesn't resolve isn't necessarily a typo — check the catalogue for its replacement.

Path Rules

Always use ${CLAUDE_PLUGIN_ROOT} for plugin files or fully resolved absolute paths for project files, passed to Read, Write, Edit, or Glob — never ~, which these tools don't expand and instead create as a literal ~ directory.

Never force-add .geniro/ paths

git add -f on a .geniro/ path makes ignored files visible in IDE Source Control panels, and one "Discard All Changes" click then becomes a data-loss vector. For content that genuinely should be tracked, use .gitignore negation (!.geniro/actions/ plus !.geniro/actions/**). A hook blocks the force-add.

Read the full file on GitHub · 98 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. 4d ago Changed · +6 lines · +265 tokens per session 97d7e5554c86
  2. 10d ago First seen · 92 lines · 2,124 tokens per session scan A 5a0a1a7efb9c

Subscribe to this mod's changes

geniro-claude-harness CLAUDE.md is an instructions file published in the GitHub repository geniro-io/geniro-claude-harness (8 stars, last pushed today), licensed Apache-2.0. It adds 2,389 tokens to every session, about $0.0119 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 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