Threadwork CLAUDE.md

Instructions for Threadwork, a Claude Code plugin for structured development workflows, persistent memory, and issue tracking. It describes the plugin's Markdown skills, commands, hooks, configuration, and tests.

In plain words
What is it for?
Use it when editing Threadwork commands, skills, session hooks, configuration schemas, examples, or tests, and when running its static validation script.
Why use it?
It gives the coding agent the repository's workflow and testing rules so changes fit the plugin's structure and can be checked consistently.

Instructions file

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 instructions/jpm1118/threadwork/claude-md
Clone the repo
git clone --depth 1 https://github.com/JPM1118/Threadwork
Per session 878 This file is loaded in full into every session.
When invoked 878 The same file — it is already loaded in full.
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 $0.00878 $0.00878
Opus 5 $0.00439 $0.00439
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 2d ago against content hash 4a7dcba7508a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Threadwork 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 2d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Threadwork is a Claude Code plugin for structured development workflows with persistent memory. It combines workflow orchestration patterns from Superpowers with persistent issue tracking from Beads.

Type: Claude Code plugin (pure Markdown skills/commands + configuration files) No build process - the plugin is ready to use as-is

Testing

# Run static validation tests (validates JSON/YAML configs, skill files exist, hook outputs)
./tests/run-static-tests.sh

The tests validate: plugin manifest, hook JSON output, all 20 SKILL.md files, schema validity, and example configuration.

Pressure testing and E2E tests are manual - see tests/TESTING_STRATEGY.md for procedures.

Architecture

Plugin Structure

commands/           User-facing commands (/init, /finish-and-close)
skills/             20 reusable workflow skills (Markdown instructions)
hooks/              Session lifecycle hooks (session-start.sh)
schemas/            JSON Schema for .threadwork.yaml validation
examples/           Example configuration

Core Workflow

The plugin implements this lifecycle:

  1. /init - Create .threadwork.yaml, initialize Beads on beads-metadata branch
  2. brainstorming skill - Explore problem space
  3. worktree-setup skill - Create git worktree for isolated development
  4. beads-backed-planning skill - Create epic + tasks in Beads
  5. beads-tdd-execution skill - Implement each task (RED-GREEN-REFACTOR)
  6. verification-before-completion skill - Require evidence before claiming done
  7. code-review skill - Quality gate between tasks
  8. finishing skill - Assess readiness, determine landing strategy
  9. /finish-and-close - Merge/PR and cleanup

Key Architectural Principles

  1. Beads is source of truth - Persistent task tracking survives conversation compaction
  2. Linear task dependencies - bd ready always returns exactly one next task
  3. TDD enforced - RED (failing test) before GREEN (implementation), always
  4. Subagents never create issues - They report discoveries; orchestrator decides
  5. Always use bd --no-daemon - Avoids worktree path confusion
  6. Skill-invokes-command pattern - Skills handle judgment; commands handle deterministic execution
  7. One Beads issue per task - Tasks contain multiple TDD steps in their design field

Read the full file on GitHub · 91 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. 2d ago First seen · 91 lines · 878 tokens per session scan A 4a7dcba7508a

Subscribe to this mod's changes

Threadwork CLAUDE.md is an instructions file published in the GitHub repository JPM1118/Threadwork (5 stars, last pushed 8mo ago), licensed MIT. It adds 878 tokens to every session, about $0.0044 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.