build

A command workflow that takes the next unfinished task from a repository's TODO list and implements it.

In plain words
What is it for?
Use it to complete the next TODO item, verify the implementation, update TODO.md and REVIEW.md, and create a conventional commit.
Why use it?
It keeps work in the planned order and requires the relevant specifications, tests, quality checks, review notes, and task updates to be handled together.

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/pinecone-io/rings/build
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

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 315 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 $0.00000 $0.00315
Opus 5 $0.00000 $0.00158
Sonnet 5 $0.00000 $0.00063
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash 4ab9c7da8e8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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.

.claude/commands/build.md · 34 lines

What it actually says

Implement the next task from the TODO list.

Steps

1. Find the next task

Read TODO.md at the repo root.

Find the first task (### Task N: ...) that has unchecked steps (- [ ]). Tasks are ordered by dependency — do not skip to a later task if an earlier one is incomplete.

If there are no unchecked tasks, tell the user the TODO list is complete and stop.

Tell the user which task you are starting before proceeding.

2. Check if the task is already done

Explore the code to see if the task has already been implemented. If it has, mark all its steps done (- [x]) in TODO.md and stop.

3. Implement

Work through all steps of the chosen task. Follow the CLAUDE.md quality gates:

  • Read the relevant spec in specs/ before implementing
  • Implement first, then write tests — no stubs or placeholders
  • just validate must pass (runs fmt-check, lint, and tests)
  • No unwrap() or expect() in production code
  • Update REVIEW.md with decisions, conflicts, or open questions

When all steps are complete, mark each finished step in TODO.md (- [ ]- [x]).

Commit following the conventional commit rules in CLAUDE.md. Do not push unless asked.

Report: task name, what was implemented, and whether any REVIEW.md entries were added.

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 · 34 lines · 0 tokens per session scan A 4ab9c7da8e8d

Subscribe to this mod's changes

build is a command published in the GitHub repository pinecone-io/rings (5 stars, last pushed 16d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 315 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 2026-08-31.