make-this

A setup procedure for a supervised multi-agent coding loop, where agents work in separate Git worktrees and branches while sharing task tracking and file-ownership rules.

In plain words
What is it for?
Use it to install the loop structure, interview the user about agents and ownership, and create shared instructions, prompts, radar files, and journals.
Why use it?
It organizes parallel coding work and adds human approval points for risky changes.

Skill for Claude CodeCodex

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/anshulixyz/multi-agent-loop-kit/make-this
Any agent
npx skills add anshulixyz/multi-agent-loop-kit --skill make-this
Clone the repo
git clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kit

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 459 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 $0.00041 $0.00459
Opus 5 $0.00020 $0.00230
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 2d ago against content hash a095222eef22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make-this 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.

skills/make-this/SKILL.md · 43 lines

What it actually says

Set up a multi-agent loop in this repo

The Multi-Agent Loop Kit turns a single repo into a supervised loop where several AI coding agents work in parallel — each in its own git worktree and branch, each owning a slice of the codebase, all visible on a shared radar, with a human approving the risky moves.

To set it up, do exactly what the /loop:make-this command does:

  1. Install the scaffolding into the current repo (never overwrites; writes .loopkit copies on collision):

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/install-into-repo.sh" .
    

    Report any .loopkit files that need a manual merge, especially AGENTS.md.

  2. Run the setup interview — read ${CLAUDE_PLUGIN_ROOT}/prompts/setup-interview.md and follow it: inspect the repo, interview the user about which agents to create, how to split ownership, and the goals, then propose AGENTS.md, LOOP_RADAR.md, ownership rules, per-agent prompts, and journals — pausing for approval before writing.

Once set up, the operator runs the loop with the other commands: /loop:spawn to create an agent, /loop:status and /loop:tick to see what everyone's doing, /loop:standup and /loop:approvals for the decision queue.

If the repo is not a git repository, flag that the kit relies on git worktrees and offer to git init first.

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 · 43 lines · 41 tokens per session scan A a095222eef22

Subscribe to this mod's changes

make-this is a skill published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 459 once invoked, about $0.0002 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

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

griddynamics/rosetta · 32 tokens

nobrainer-ultra

Use when the owner says nb-ultra, nb-flow, nb-workflow, ultracode, or asks to set up, upgrade, or reconcile a project's agent workflow; or wants one non-trivial task taken from brief requirements through a complete skill-routed plan, guarded autonomous execution, useful multi-session work and final evidence audit.

nobrainer-tech/nobrainer-tech-skills · 73 tokens

nobrainer-autoimprove

Use when the owner says nb-autoimprove, deep-autoresearch, code-autoresearch, nobrainer-capture-lesson, or nobrainer-continuous-improvement; asks to improve a skill or prompt; or wants a measurable bounded baseline-variant-evaluation loop instead of one subjective rewrite.

nobrainer-tech/nobrainer-tech-skills · 70 tokens

nobrainer-dispatcher

Use when the owner says nb-dispatcher or nobrainer-dispatcher, or when an approved execution map has multiple queued work units that require ready-set selection, dependency-aware ordering, bounded parallel batches, retry scheduling, or routing audited results to the next queued unit; do not use for one coherent task…

nobrainer-tech/nobrainer-tech-skills · 89 tokens

nobrainer-review

Use when the owner says nb-review, deep-audit, deep-code-review, or deep-autoreview; explicitly requests an evidence-gated CLOSEOUT, adversarial BUGHUNT or RELEASEGATE; or needs final findings filtered to verified actionable defects. Use nobrainer-build for ordinary implementation and correction work.

nobrainer-tech/nobrainer-tech-skills · 67 tokens

nobrainer-writing

Use when the owner says nb-write, nobrainer-writing, nobrainer-style, or nobrainer-human-like, or asks to draft, rewrite, compress, humanize, edit, or review user-facing prose such as a message, comment, document, README, report, summary, email, post, or release note; maximize useful information per word without…

nobrainer-tech/nobrainer-tech-skills · 92 tokens