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 commands/anshulixyz/multi-agent-loop-kit/make-thisgit clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kitWhat 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 | $0.00016 | $0.00332 |
| Opus 5 | $0.00008 | $0.00166 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
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.
What it actually says
Turn the current repository into a supervised multi-agent loop.
-
Run the installer. With no argument it installs into your repo's primary checkout (safe to run from a subdirectory); pass a path in
$ARGUMENTSto target a different repo:bash "${CLAUDE_PLUGIN_ROOT}/bin/loop-make-this" $ARGUMENTSIt never overwrites existing files — on any collision it writes a
<name>.loopkitcopy beside yours and lists it. Read that output and tell the user which files (if any) need a manual merge, especiallyAGENTS.md. (A relative target path is resolved from the repo root, not your current subdirectory; use an absolute path if you mean somewhere else.) -
Then run the setup interview. Read
${CLAUDE_PLUGIN_ROOT}/prompts/setup-interview.mdand follow it: inspect this repo, interview the user about agents/ownership/goals, and proposeAGENTS.md,LOOP_RADAR.md, ownership rules, per-agent prompts, and journals — stopping for the user's approval before writing anything substantive.
Do not skip the interview — installation only copies the scaffolding; the interview is what
adapts it to this repo. If the repo is not a git repository, point out that the kit relies on
git worktrees and offer to run git init.
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 · 29 lines · 16 tokens per session scan A b3f5f549298d
make-this is a command published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 332 once invoked, about $0.0001 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 commands, from other repositories
unlatch
Confirmed toggle for latch Unlatched mode.
latch-compact
Manually trigger a latch compaction for the current session.
latch-gate
Manual gate (LLM go/no-go judgement) on a coding/build request.
latch-tree
Rebuild the hierarchical cluster/summary tree for this project's KB.
latch-budget-approve
Unlock the rest of today for unlimited latch LLM invocations in this project.
latch-decay
Apply weekly decay + promote staging nodes that cleared the refcount bar.