agentmods.dev

magi-workflow CLAUDE.md

magi-workflow CLAUDE.md is an instructions file for coding agents from howar31/magi-workflow. It costs 626 tokens per session, scanned A, original, MIT.

Project instructions for MAGI, a multi-command workflow for planning and reviewing software changes. They describe commands, helper agents, project states, document rules, and commits.

In plain words
What is it for?
Use them when working with MAGI commands, checking project state, reviewing plans, validating specification changes, or creating commits.
Why use it?
They give coding agents a shared way to understand the project and follow its required process.

Instructions file

not rated 2 4d ago A scan 626 tokens original MIT
View the source file howar31/magi-workflow
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/howar31/magi-workflow/claude-md
Clone the repo
git clone --depth 1 https://github.com/howar31/magi-workflow

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 magi-workflow CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/howar31/magi-workflow/claude-md.svg)](https://agentmods.dev/instructions/howar31/magi-workflow/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/howar31/magi-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/howar31/magi-workflow/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 626 This file is loaded in full into every session.
When invoked 626 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 $0.00626 $0.00626
Opus 5 $0.00313 $0.00313
Sonnet 5 $0.00125 $0.00125
Haiku 4.5 $0.00063 $0.00063

Measured 3d ago against content hash 7e5358d4d240, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

magi-workflow 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 3d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What this is

Multi-CLI MAGI orchestration plugin for code/plan review. → SPEC.md

Slash commands

Per-command contract in skills/<name>/SKILL.md. → SPEC.md §Slash commands

Subagents

→ agents/developer.md, agents/reviewer.md

Project state model

8 filesystem-derived states; SSOT is scripts/shared/detect-state.sh. → SPEC.md §Project state model

Project document tiers

→ SPEC.md §Project document tiers

Spec deltas

PLAN/SPEC carry a ## Spec deltas section declaring expected modifications to root SPEC.md / CLAUDE.md / magi/PRD.md / magi/TECHSTACK.md. Evaluated by /magi:review-plan; verified by /magi:commit §2.5 (D1/D2/D3). → SPEC.md §Spec deltas

Commits

  • /magi:commit is the single in-project commit path (sprint + standalone). Independent of ~/.claude/skills/commit/.
  • Before any commit, check whether .claude-plugin/plugin.json needs a bump per SPEC.md §Plugin versioning. Bump goes in the same commit.
    • When bumping, also update the version badge in README.md (line near shields.io/badge/version-vX.Y.Z) in the same commit.

Run / test

./scripts/shared/preflight.sh    # CLI healthcheck
./test/e2e-smoke.sh              # real CLI smoke test
./test/e2e-fallback.sh           # mock-adapter fallback test

Conventions

  • Bash 3.2 compatible (no mapfile, readarray, declare -A, ${var^^})
  • set -uo pipefail on every script; avoid set -e; init arrays with arr=()
  • jq for JSON; no setsid (Linux-only); prefer gtimeout over timeout
  • Shellcheck-friendly (# shellcheck source= annotations)
  • File naming: project SSOT docs uppercase (PLAN.md, SPEC.md, TASKS.md, WORKS.md, DRIFT.md, PRD.md, TECHSTACK.md, BACKLOG.md); plugin internals kebab-case
  • Language: English for CLAUDE.md, SPEC.md, references/, skills/**/SKILL.md, agents/*.md; zh-TW for README.md and user-facing prompts; English for code comments

Lessons

When magi misbehaves in a real session and we have to re-correct Claude's shortcut, add a one-line entry to references/LESSONS.md under the relevant skill section. Empirical incidents only — no theoretical "what if" entries.

Read the full file on GitHub · 44 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. 3d ago First seen · 44 lines · 626 tokens per session scan A 7e5358d4d240

Subscribe to this mod's changes

magi-workflow CLAUDE.md is an instructions file published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 4d ago), licensed MIT. It adds 626 tokens to every session, about $0.0031 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 agentsPlanningai-agentsanthropicclaude-codeclaude-code-pluginclaude-plugin
Related

Other instructions, from other repositories

markifact-mcp GEMINI.md

Instructions for markifact/markifact-mcp, covering markifact, the 8 tools, discover → inspect → run, connection vs account and reporting workflow.

markifact/markifact-mcp · 838 tokens

Version-Sentinel CLAUDE.md

Instructions for KSEGIT/Version-Sentinel, covering version sentinel, project structure, supported ecosystems, how it works and prerequisites.

KSEGIT/Version-Sentinel · 678 tokens

Version-Sentinel GEMINI.md

Instructions for KSEGIT/Version-Sentinel, covering version-sentinel (gemini cli extension), how it works, intentional pins, auditing drift and escape hatch.

KSEGIT/Version-Sentinel · 506 tokens

Looptimal CLAUDE.md

Instructions for Renn-Labs/Looptimal, covering looptimal — repo guidance for ai agents, build journal — capture the concepts, not the changelog and — .

Renn-Labs/Looptimal · 449 tokens

superpowers-graph CLAUDE.md

Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.

RonMizrahi/superpowers-graph · 738 tokens

embedded-systems-architect AGENTS.md

Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.

Zachariah9420/embedded-systems-architect · 177 tokens