setup-codebase-harness

setup-codebase-harness is a skill for Claude Code from gabrielmoreira/agent-skills-mirror. It costs 103 tokens per session (1,438 once invoked), scanned A, original, MIT.

A setup guide for making a code repository easy for an AI agent to understand, run, test, and maintain. It organizes documentation, development tools, checks, and shipping practices around the repository.

In plain words
What is it for?
Use it when onboarding an agent to a repository or improving the repository's support for agent-driven development. It helps assess missing documentation, local setup, end-to-end checks, verification, and commit practices.
Why use it?
It reduces the guesswork that makes agents struggle with unfamiliar codebases. It also creates feedback loops that catch problems before changes are shipped.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Good fit Use it when onboarding an agent to a repository or improving the repository's support for agent-driven development. It helps assess missing documentation, local setup, end-to-end checks, verification, and commit practices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness
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.

Any agent
npx skills add gabrielmoreira/agent-skills-mirror --skill setup-codebase-harness
Clone the repo
git clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirror

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 setup-codebase-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness/github.svg)](https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness)
Your own site
<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness/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 setup-codebase-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/setup-codebase-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,438 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00103 $0.01438
Opus 5 $0.00051 $0.00719
Sonnet 5 $0.00021 $0.00288
Haiku 4.5 $0.00010 $0.00144

Measured 9d ago against content hash 7722757f45e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

setup-codebase-harness 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.

mirrors/repos/AI-Builder-Club@skills/skills/setup-codebase-harness/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up the codebase harness

Harness engineering: the model is fixed — what you engineer is the scaffolding around it (the environment, the docs, the feedback loops) so an agent can build and verify software with minimal human attention. Humans steer; agents execute. Your job is to make the repo legible, executable, and verifiable.

Work incrementally and depth-first: assess what exists, build the one missing capability, use it to unlock the next. Don't boil the ocean — set up what the repo actually needs. When the agent struggles, the fix is almost never "try harder" — ask "what capability is missing, and how do I make it legible and enforceable?" and add it.

This skill orchestrates the focused sub-skills: dev-local-setup, e2e-setup, crabbox-setup (cloud/parallel), and verifier-setup (scaffolds a repo-specific /verify loop; supersedes the older pr skill).

0. Assess

Survey the repo: stack, package manager, services/ports, infra deps, existing docs/tests/CI, and the implicit rules (buried in READMEs, PR comments, people's heads). Note what's missing per pillar below.

1. Legible — the agent can reason about the repo

What the agent can't see doesn't exist. Knowledge in chat threads / heads is invisible — push it into versioned, repo-local artifacts.

  • a) Map, not manual. Shrink the root agent doc (AGENTS.md / CLAUDE.md) to a ~100-line table of contents: one-line overview, project tree, golden rules (the hard invariants), and a "where to look" table. Move the depth into a structured docs/ system-of-record (architecture, frontend, testing, domain topics) with a docs/index.md. A monolithic instruction file rots and crowds out the task — keep the map small and stable, disclose detail progressively.
  • b) Custom lints with remediation. Promote the prose golden rules into mechanical checks — human taste captured once, enforced everywhere, every run. One lint per invariant (layering / dependency direction, naming, no-any, forbidden imports, file-size, structured logging). Write the error message to inject the fix ("X isn't allowed here — do Y") so the remediation lands in agent context. Wire them into the repo's linter + CI.
  • c) Queryable code graph. Index the repo with codebase-memory-mcp so the agent traces callers, data flow, and architecture from a knowledge graph instead of blind grepping — faster, more precise navigation on large codebases.
  • d) (later) Keep docs honest. A freshness / doc-gardening pass that flags docs that no longer match the code and opens fix-up PRs.

Read the full file on GitHub · 101 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. 9d ago First seen · 101 lines · 103 tokens per session scan A 7722757f45e6

Subscribe to this mod's changes

setup-codebase-harness is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,438 once invoked, about $0.0005 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 2026-09-03.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens