A workflow for examining a Git repository's Claude Code setup, including its skills, hooks, agents, and project instructions.

Use it with a Git repository found during research to produce proposals for adopting new skills, automation, or working patterns.

It helps identify useful practices in another repository and compare them with the setup you already have.

harvest — Skill for Claude Code by dixus: A workflow for examining a Git repository's Claude Code…

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/dixus/claudeframework/harvest

Any agent

npx skills add dixus/claudeframework --skill harvest

Clone the repo

git clone --depth 1 https://github.com/dixus/claudeframework

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dixus/claudeframework/harvest.svg)](https://agentmods.dev/skills/dixus/claudeframework/harvest)

Your own site

<a href="https://agentmods.dev/skills/dixus/claudeframework/harvest"><img src="https://agentmods.dev/badge/skills/dixus/claudeframework/harvest.svg" alt="Measured on agentmods" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,466 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.02466
Opus 5	$0.00024	$0.01233
Sonnet 5	$0.00010	$0.00493
Haiku 4.5	$0.00005	$0.00247

Measured 5d ago against content hash 2360987a62fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

harvest 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.

.claude/skills/harvest/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clone a Git repository, analyze its Claude Code setup (skills, hooks, agents, rules, CLAUDE.md), compare against this framework, and generate adoption proposals.

$ARGUMENTS must include a Git-cloneable URL. Optional flags:

--clean — delete the cloned repo after analysis (harvest report is preserved)
--deep — detailed line-level comparison for new and enhancement items

Phase 0 — Validate and prepare

Parse $ARGUMENTS for the repo URL and flags (--clean, --deep)
Extract <owner>/<repo> from the URL. Derive a slug: <owner>-<repo> (e.g. anthropics-skills, travisvn-awesome-claude-skills)
Idempotency check: if references/repos/<slug>/processed/.done exists, report "Already harvested — run with a different repo or delete the marker to re-harvest" and stop
Check .claude/references/scout-registry.md — if the URL exists with status fetched and type repo, also stop (already analyzed)
Load framework inventory. Read and catalog our current capabilities:
- All skill names and descriptions: glob .claude/skills/*/SKILL.md, extract name and description from frontmatter
- All agents: glob .claude/agents/*.md
- All hooks: glob .claude/hooks/*
- All rules: glob .claude/rules/*.md
- CLAUDE.md top-level headings
- This inventory is used for comparison in Phase 3

Phase 1 — Clone

Create the target directory if needed: references/repos/
Run: git clone --depth 1 <repo-url> .claude/references/repos/<slug>/
If clone fails (private repo, invalid URL, network error), report the error and stop — do not create partial state
Log: "Cloned → references/repos// (shallow)"

Phase 2 — Assess

Check the cloned repo for framework indicators:
- .claude/ directory (or .claude-code/, claude/)
- CLAUDE.md (or .cursorrules, .windsurfrules — note as alternative AI config)
- package.json, pyproject.toml, Cargo.toml (identify tech stack)
- .mcp.json or mcp_config.json (MCP server config)

Read the full file on GitHub · 207 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.

5d ago First seen · 207 lines · 48 tokens per session scan A 2360987a62fb

Subscribe to this mod's changes

harvest is a skill published in the GitHub repository dixus/claudeframework (10 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 2,466 once invoked, about $0.0002 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.

Building agents Research

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