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.
npx agentmods add instructions/jpm1118/threadwork/claude-mdgit clone --depth 1 https://github.com/JPM1118/ThreadworkWhat 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 | $0.00878 | $0.00878 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
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.
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:
/init- Create.threadwork.yaml, initialize Beads onbeads-metadatabranchbrainstormingskill - Explore problem spaceworktree-setupskill - Create git worktree for isolated developmentbeads-backed-planningskill - Create epic + tasks in Beadsbeads-tdd-executionskill - Implement each task (RED-GREEN-REFACTOR)verification-before-completionskill - Require evidence before claiming donecode-reviewskill - Quality gate between tasksfinishingskill - Assess readiness, determine landing strategy/finish-and-close- Merge/PR and cleanup
Key Architectural Principles
- Beads is source of truth - Persistent task tracking survives conversation compaction
- Linear task dependencies -
bd readyalways returns exactly one next task - TDD enforced - RED (failing test) before GREEN (implementation), always
- Subagents never create issues - They report discoveries; orchestrator decides
- Always use
bd --no-daemon- Avoids worktree path confusion - Skill-invokes-command pattern - Skills handle judgment; commands handle deterministic execution
- One Beads issue per task - Tasks contain multiple TDD steps in their design field
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.
- 2d ago First seen · 91 lines · 878 tokens per session scan A 4a7dcba7508a
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.
Other instructions, from other repositories
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
clawchat-plugin-connect AGENTS.md
Instructions for XMethues/clawchat-plugin-connect, covering agent skills, issue tracker, triage labels and domain docs.
autonomous-dev CLAUDE.md
Claude Code instructions for akaszubski/autonomous-dev, covering autonomous-dev, critical rules, maintainer escape hatches, architecture and code navigation.
icloud-reminders-mcp CLAUDE.md
Claude Code instructions for Lingnik/icloud-reminders-mcp, covering icloud-reminders-mcp — project conventions, backlog: github issues, always, secrets, architecture and testing.