automagik-hive: Command for Claude Code

.claude/commands/forge.md

forge is a command for Claude Code from namastexlabs/automagik-hive. It costs 0 tokens per session (820 once invoked), scanned A, original, MIT.

A command that turns an approved wish into grouped implementation tasks. It discovers the work, drafts a plan, waits for human approval, and then creates one task for each approved group.

In plain words
What is it for?
Summarizing goals and constraints, proposing task groups and dependencies, recording a planning report, and creating tracked tasks with branches and assigned responsibilities.
Why use it?
It organizes a large request into clear pieces while preventing tasks from being created before a person approves the proposed grouping.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is namastexlabs/automagik-hive's own configuration. It tells Claude Code how to work on automagik-hive 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 automagik-hive configures →

Reuse

Borrowing it

Nothing to install: this file belongs to namastexlabs/automagik-hive. 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/namastexlabs/automagik-hive/main/.claude/commands/forge.md
Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-hive

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 forge

README.md
[![agentmods](https://agentmods.dev/badge/commands/namastexlabs/automagik-hive/forge/github.svg)](https://agentmods.dev/commands/namastexlabs/automagik-hive/forge)
Your own site
<a href="https://agentmods.dev/commands/namastexlabs/automagik-hive/forge"><img src="https://agentmods.dev/badge/commands/namastexlabs/automagik-hive/forge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for forge

Your own site · 80×15
<a href="https://agentmods.dev/commands/namastexlabs/automagik-hive/forge"><img src="https://agentmods.dev/badge/commands/namastexlabs/automagik-hive/forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 820 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 $0.00820
Opus 5 $0.00000 $0.00410
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 9d ago against content hash 4c9e7c7712c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

forge 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 9d 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/commands/forge.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge - Wish Breakdown & Task Creation


description: Analyze an approved wish, propose task groups, gather human approval, then create forge tasks via forge-master

[CONTEXT]

  • Use after a wish is READY_FOR_EXECUTION and the human wants to spin up isolated forge tasks.
  • Output includes a planning report and, once approved, calls to forge-master for each group.
  • Every action is recorded in genie/reports; final chat response references task IDs and the report path.

[SUCCESS CRITERIA] ✅ Planning report saved to genie/reports/forge-plan-<wish-slug>-<YYYYMMDDHHmm>.md (UTC). ✅ Human explicitly approves grouping before any task creation. ✅ Exactly one forge task per approved group; branches reference the origin branch. ✅ Chat reply lists tasks, branch names, and links to the report.

[NEVER DO] ❌ Create forge tasks without human approval. ❌ Fragment work beyond the approved grouping. ❌ Omit dependency chains or agent responsibilities. ❌ Forget to capture the Death Testament path.

<task_breakdown>
1. [Discovery] Summarize wish goals, constraints, and existing progress.
2. [Planning] Propose logical task groups with agent and evidence expectations.
3. [Approval] Present plan; wait for human confirmation or revisions.
4. [Creation] Invoke `forge-master` once per approved group and record results.
</task_breakdown>

Step 1 – Discovery

  • Load /genie/wishes/<slug>-wish.md.
  • Note status, scope, risks, and orchestration strategy.
  • Identify natural groupings that map to single-agent execution.

Step 2 – Plan Draft

  • For each proposed group capture:
    • Name/slug (short kebab-case)
    • Scope of work
    • Primary agent (e.g., hive-coder, hive-tests)
    • Expected evidence (Death Testament references, tests, QA)
    • Dependencies
  • Store the draft plan in genie/reports/forge-plan-<wish-slug>-<timestamp>.md under a “Planning” section.
  • Share a concise summary in chat and ask for approval (Yes/No/Adjust).

Step 3 – Approval Loop

  • Update the plan report until the human explicitly approves.
  • Record approval (time, initials) in the report before proceeding.

Read the full file on GitHub · 82 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. 9d ago First seen · 82 lines · 0 tokens per session scan A 4c9e7c7712c6

Subscribe to this mod's changes

forge is a command published in the GitHub repository namastexlabs/automagik-hive (24 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 820 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 2026-08-30.