build

A build command for carrying out an approved coding plan one task at a time. TDD, or test-driven development, means writing or running a failing test before implementing the change.

In plain words
What is it for?
Use it to implement feature tasks on a separate branch, run tests and quality checks, record evidence, and continue to review and validation stages.
Why use it?
It turns a plan into checked work by requiring tests, implementation, and validation, while also checking that the planned scenarios are covered.

Command

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/galando/temper/build
Clone the repo
git clone --depth 1 https://github.com/galando/temper
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 599 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 $0.00008 $0.00599
Opus 5 $0.00004 $0.00300
Sonnet 5 $0.00002 $0.00120
Haiku 4.5 $0.00001 $0.00060

Measured yesterday against content hash f40c8f4f59e9, 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 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.

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.

commands/build.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build: Execute Plan

Goal: Implement approved plan task by task with TDD and graduated quality gates.

Execution

Full methodology: Read $CLAUDE_PLUGIN_ROOT/reference/build.md

Subprocess Mode

If $CLAUDE_PLUGIN_ROOT/scripts/temper config get stages.subprocess false returns true, don't run the methodology inline (skip the reference read and Quick Reference below). Launch the same isolated subprocess /temper uses — model from temper model build, prompt: "Follow $CLAUDE_PLUGIN_ROOT/agents/build.md exactly. Spec: .temper/specs/{feature-slug}. Standalone run — pass --spec-path .temper/specs/{feature-slug} to every temper gate call." Print the returned box verbatim, then run the gate + report per Deterministic Gate below (the subprocess already recorded the RED/GREEN evidence and ticked tasks.md); auto-chain to /temper:review/temper:check as usual — the human gate stays in this context either way.

Quick Reference

  1. Load plan from .temper/specs/{feature}/tasks.md
  2. Verify feature branch (create if on main)
  3. For each task: test from intent.md scenario (RED) → implement (GREEN) → validate
  4. Scenario coverage gate: every intent.md scenario must have a passing test
  5. Success criteria gate: code-validated criteria must be present (WARN only)
  6. Resumes interrupted builds from checkpoint
  7. After all tasks: run temper gate build --spec-path .temper/specs/{feature-slug} — see Deterministic Gate below
  8. Auto-chain → /temper:review → /temper:check
  9. Report results, ask to commit

Active Skills

  • Temper Core — stack detection, pack resolution, quality gates
  • Context Engineering — load hierarchical context at stage start (rules → arch → source → errors, under 2K lines/task)
  • Source-Driven Development — before writing framework-specific code: detect installed version → fetch current docs → cite sources → surface API conflicts. Skip for plain logic or known patterns

Deterministic Gate

Follow $CLAUDE_PLUGIN_ROOT/agents/build.md steps 2-3 (record RED/GREEN test evidence via temper evidence add --stage build --phase red|green) as you implement each task, then run temper gate build --spec-path .temper/specs/{feature-slug} before reporting results — same reason as Plan/Review/Check: skipping this leaves temper gate commit unable to see that build happened at all. Pass --spec-path explicitly rather than relying on temper state having been initialized.

Read the full file on GitHub · 53 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 · 53 lines · 8 tokens per session scan A f40c8f4f59e9

Subscribe to this mod's changes

build is a command published in the GitHub repository galando/temper (15 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 599 once invoked, about $0.0000 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 2026-08-30.