go

go is a skill for Claude Code, Codex from howar31/magi-workflow. It costs 90 tokens per session (3,318 once invoked), scanned A, original, MIT.

A workflow command that executes the next unfinished tasks from a sprint’s TASKS.md by assigning them to a development subagent.

In plain words
What is it for?
Use it to run sprint tasks, optionally in parallel, verify the reported changes, update the development log, and pause before committing.
Why use it?
It organizes task execution, records progress in WORKS.md, checks project state, and prevents work from proceeding when required setup or rules block it.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the magi plugin — 15 skills, 2 agents shipped together

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/howar31/magi-workflow/go
Any agent
npx skills add howar31/magi-workflow --skill go
Clone the repo
git clone --depth 1 https://github.com/howar31/magi-workflow

Made for: Claude Code, Codex.

Or install magi, the plugin that ships this one along with the rest of its 15 skills, 2 agents.

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 go

README.md
[![agentmods](https://agentmods.dev/badge/skills/howar31/magi-workflow/go.svg)](https://agentmods.dev/skills/howar31/magi-workflow/go)
Your own site
<a href="https://agentmods.dev/skills/howar31/magi-workflow/go"><img src="https://agentmods.dev/badge/skills/howar31/magi-workflow/go.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,318 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.

ModelPer sessionOnce invoked
Fable 5 $0.00090 $0.03318
Opus 5 $0.00045 $0.01659
Sonnet 5 $0.00018 $0.00664
Haiku 4.5 $0.00009 $0.00332

Measured 3d ago against content hash 458268d165aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

go 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.

skills/go/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/magi:go — execute tasks via subagent

Enforcement: rigid. Once /magi:go starts, every step in this skill body must be executed in order. Do not shortcut the developer brief, do not skip WORKS.md updates, do not accept subagent reports without verification. If something blocks you, stop and report — do not improvise around it.

You are the coordinator. Read TASKS.md, dispatch magi-developer to do the work, collect results, update WORKS.md, and stop. You do not write production code yourself.

0. Preflight

PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
[[ -z "$PLUGIN_ROOT" ]] && PLUGIN_ROOT="$(cd "$(dirname "$BASH_SOURCE[0]")/../.." 2>/dev/null && pwd)"
USER_CONFIG="$HOME/.config/magi-workflow/config.json"

If config missing → tell user to run /magi:setup.

0.5. State preflight (auto-refuse if not allowed)

Run scripts/shared/detect-state.sh and check disallowed_skills["go"]. If present, surface reason + suggest in user's language and abort.

STATE_JSON=$(bash "$PLUGIN_ROOT/scripts/shared/detect-state.sh")
blocked=$(jq -r '.disallowed_skills["go"] // empty' <<<"$STATE_JSON")
if [[ -n "$blocked" ]]; then
  reason=$(jq -r '.disallowed_skills["go"].reason' <<<"$STATE_JSON")
  suggest=$(jq -r '.disallowed_skills["go"].suggest' <<<"$STATE_JSON")
  echo "Cannot run /magi:go: $reason"
  echo "Suggested: $suggest"
  exit 1
fi
hotfix=$(jq -r '.hotfix_mode' <<<"$STATE_JSON")

--force skips preflight (advanced/recovery only).

If hotfix=true, the sprint has a HOTFIX.md and no TASKS.md is required. Build a single-task brief from HOTFIX.md (Repro / Root cause / Fix / Test) and dispatch directly — skip §1's TASKS.md scanning.

1. Locate sprint + task selection

Find the sprint folder (most recent or --sprint <num>-<slug>).

Read TASKS.md. Determine the next batch of work:

  • Default: pick the next milestone with at least one - [ ] task. Within that milestone, all sequential - [ ] tasks become this batch.
  • --milestone N — execute milestone N specifically.
  • --task T1.2 — execute exactly that task ID.
  • --parallel — if the chosen milestone has 🔀 lanes, dispatch one developer per lane in parallel. Without this flag, lanes are executed sequentially.

Read the full file on GitHub · 339 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 · 339 lines · 90 tokens per session scan A 458268d165aa

Subscribe to this mod's changes

go is a skill published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 3,318 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

specify-meta

Scaffold, status-check, and manage specification directories. Use when creating a new spec, reading spec status, transitioning between phases, or logging decisions on a spec in .start/specs/.

rsmdt/the-startup · 42 tokens

feature-prioritization

RICE, MoSCoW, Kano, and value-effort prioritization frameworks with scoring methodologies and decision documentation. Use when prioritizing features, evaluating competing initiatives, creating roadmaps, or making build vs defer decisions.

rsmdt/the-startup · 51 tokens

user-story-generator

Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want"…

lenar-amirov/product-pipeline-public · 76 tokens

ambiguity-resolver

Structures a brief HANDED DOWN by a stakeholder (boss, exec, another team) into a one-page problem statement with scope boundaries and a named decision owner. Use when the PM says "мне спустили задачу", "I've been asked to look into Y", "руководство хочет X", "CEO попросил разобраться" — a request the PM didn't…

lenar-amirov/product-pipeline-public · 98 tokens

project-init

Framework for creating project documentation from specs — reviews, research, architecture, planning, task decomposition into slices, and optional Jira sync. Triggers on "storm the spec", "analyze spec", "project init", "init project from spec", "проанализируй ТЗ", "разбери ТЗ", "создай документацию по ТЗ", or when…

UnBergant/bergant-workflow · 129 tokens

lifecycle

Orchestrate feature lifecycle — track steps, enforce gates, dispatch sub-agents. Use when starting a new task, checking lifecycle status, or advancing to the next step.

UnBergant/bergant-workflow · 38 tokens