build-loop

A command that follows a checklist in PLAN.md, sending each task to a builder and a reviewer before committing it to Git, a system for tracking code changes.

In plain words
What is it for?
Use it to execute an existing coding plan task by task, with review and a commit required for each completed task.
Why use it?
It keeps implementation work in small steps and prevents unreviewed or overly connected changes from being committed.

Command for Claude Code

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 commands/robconery/cassini-workshop/build-loop
Clone the repo
git clone --depth 1 https://github.com/robconery/cassini-workshop

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 936 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00021 $0.00936
Opus 5 $0.00010 $0.00468
Sonnet 5 $0.00004 $0.00187
Haiku 4.5 $0.00002 $0.00094

Measured yesterday against content hash befc783ef894, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-loop scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(one `curl` against `wrangler dev`, one `bun build` + invoke, one route
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/commands/build-loop.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

build-loop

🎯 Design for change. Each task's diff should be small, local, and behind a stable seam. The reviewer fails work that couples modules or bloats blast radius — builder should pre-empt that.

Execute the build plan in $ARGUMENTS (default: docs/PLAN.md) one task at a time. You are the orchestrator (the lead thread). You do not write feature code or review it yourself — you dispatch and gate.

Scope

  • IN: build each unchecked task, get it through review, commit it.
  • OUT: planning, writing PLAN.md, authoring specs, refactor/refinement passes. This command consumes a plan; it does not author one.

Preflight

  1. Resolve the plan: use the path in $ARGUMENTS; else docs/PLAN.md; else stop and ask — do not infer a plan.
  2. Read it. It must be a checklist of tasks (- [ ] / - [x]). If it has no checkboxes, stop and report — it is not a build plan.
  3. Confirm a clean git working tree. If dirty, stop and report; do not build on top of uncommitted changes.

The loop

For each task still unchecked (- [ ]), in order, top to bottom:

  1. Build. Dispatch a builder subagent (Agent tool, subagent_type: builder, model sonnet). Give it: the exact task text, the relevant section of PLAN.md, the files it owns, and an instruction to invoke the project's TypeScript + DB skills and run the existing specs (bun test / project test command) before reporting back. The builder does not commit.

  2. Review. Dispatch a reviewer subagent (Agent tool, subagent_type: reviewer, model opus — reviewer must be ≥ builder). It invokes security-web and simplify, reads the builder's diff, and returns a verdict: PASS or FAIL with specific findings.

  3. Recurse. If FAIL: send the findings back to a fresh builder for the same task. Repeat build → review until PASS. No cap — a task is not done until it passes code and security review. Nothing reaches git history before PASS.

Read the full file on GitHub · 85 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. yesterday First seen · 85 lines · 21 tokens per session scan A befc783ef894

Subscribe to this mod's changes

build-loop is a command published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 936 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.