set-core: Skill for Claude Code

.claude/skills/set/harvest/SKILL.md

harvest is a skill for Claude Code from tatargabor/set-core. It costs 0 tokens per session (849 once invoked), scanned A, original, MIT.

A review process for bringing useful fixes from consumer projects’ end-to-end runs back into a shared framework. End-to-end tests exercise a system through complete user-like flows rather than isolated functions.

In plain words
What is it for?
Use it to scan registered projects, inspect unresolved issues and fix commits, preview pending changes, and decide which fixes belong in the shared framework.
Why use it?
It prevents framework bugs, failed checks, and recovery problems found in downstream projects from being forgotten or fixed only locally. It also separates generally useful fixes from project-specific ones.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is tatargabor/set-core's own configuration. It tells Claude Code how to work on set-core 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 set-core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tatargabor/set-core. 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/tatargabor/set-core/main/.claude/skills/set/harvest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tatargabor/set-core

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 harvest

README.md
[![agentmods](https://agentmods.dev/badge/skills/tatargabor/set-core/harvest.svg)](https://agentmods.dev/skills/tatargabor/set-core/harvest)
Your own site
<a href="https://agentmods.dev/skills/tatargabor/set-core/harvest"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/harvest.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 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 $0.00000 $0.00849
Opus 5 $0.00000 $0.00425
Sonnet 5 $0.00000 $0.00170
Haiku 4.5 $0.00000 $0.00085

Measured yesterday against content hash 6e2bfba07d40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • harvest — 100% identical, 0 lines differ
.claude/skills/set/harvest/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harvest framework fixes from consumer project E2E runs.

Input: --project <name> (optional) — scan a single project. Without it, scans all registered consumer projects.

You are a framework maintainer. Your job is to review ISS fixes and template changes from consumer E2E runs and decide which ones should be adopted into set-core.

Quick Start

Run the harvest CLI to see unadopted framework-relevant fixes:

set-harvest --dry-run              # preview what's pending
set-harvest --project craftbrew-run-20260320-1445  # scan single project
set-harvest                        # interactive review all
set-harvest --all                  # include project-specific fixes too
set-harvest --json                 # machine-readable output

What It Scans

The harvest tool scans registered consumer projects (from set-project list) for:

  1. ISS registry — unresolved issues from .set/issues/registry.json with diagnosed root causes. Framework-relevant issues (orchestrator bugs, gate failures, stall recovery) are surfaced even if no fix commit exists. This catches bugs that were diagnosed but never fixed.
  2. ISS fix commits — commits with fix: or fix-iss- patterns that were created by the orchestration agent during E2E runs to resolve build/test/e2e gate failures
  3. Template divergences — modifications to .claude/rules/set-*.md files that were deployed by set-project init but modified by agents during the run

Issues are classified by keyword analysis of root_cause and error_summary:

  • FRAMEWORK — mentions orchestrator, engine, merger, gate, stall, redispatch, worktree
  • EXTERNAL — rate limits, API issues
  • PROJECT-SPECIFIC — app-level bugs (Suspense, Prisma, Stripe)

Commits are classified by files changed:

  • FRAMEWORK — modifies config files (package.json, playwright.config.ts, middleware.ts) → should be reviewed for adoption into planning_rules.txt or templates
  • TEMPLATE — modifies .claude/ deployed files → diff against set-core templates
  • PROJECT-SPECIFIC — only modifies app code → usually skip

Read the full file on GitHub · 70 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. yesterday First seen · 70 lines · 0 tokens per session scan A 6e2bfba07d40

Subscribe to this mod's changes

harvest is a skill published in the GitHub repository tatargabor/set-core (35 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 849 tokens. 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 2026-09-06.