A workflow for implementing exactly one already-planned piece of work after its scope is fixed. It uses project specifications, plans, task lists, and analysis checkpoints to control what gets changed.

Selecting one task, checking the scope boundary, reviewing the current analysis state, and implementing that single slice.

It prevents coding from expanding beyond the agreed task and stops work when required analysis is missing or outdated.

build-one — Skill for Claude Code and Codex by tmusser

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/tmusser/ai-engineering-skills

agentmods

npx agentmods add skills/tmusser/ai-engineering-skills/build-one

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/build-one/github.svg)](https://agentmods.dev/skills/tmusser/ai-engineering-skills/build-one)

Your own site

<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/build-one"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/build-one/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/build-one"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/build-one.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 892 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00892
Opus 5	$0.00014	$0.00446
Sonnet 5	$0.00005	$0.00178
Haiku 4.5	$0.00003	$0.00089

Measured 10d ago against content hash c798b3c9ab8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

build-one 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 10d 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/build-one/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build One

Purpose

Implement exactly one planned slice without expanding the behavioral contract or building through a known stale/required analysis checkpoint.

When to use

Use after a task is selected and scope is frozen.

Inputs

SPEC.md
PLAN.md
TODO.md
SCOPE.md or the active scope boundary
Current repo status and frozen Git base
Analysis checkpoint when present in HANDOFF.md or other current state

Workflow

Read SPEC.md, PLAN.md, and TODO.md.
Select one task.
Confirm the scope boundary. When SCOPE.md and scripts/scope_gate.py exist, run the scope gate against the frozen base before the first new implementation write. Existing FAIL or unresolved REVIEW_REQUIRED state blocks further edits.
Perform the cheap analyze-mini eligibility check using artifacts already loaded for this build:
- REQUIRED or STALE checkpoint -> invoke analyze-mini before editing.
- FRESH checkpoint -> confirm its task-defining inputs still match current state; if not, mark it STALE and invoke analyze-mini.
- missing checkpoint or NOT_NEEDED -> invoke analyze-mini only when a current trigger exists.
- Missing prior analysis alone does not require analyze-mini.
- Do not broaden discovery merely to prove that analysis is unnecessary.
If full analysis returns BLOCKED, stop before implementation and resolve the contradiction or decision.
Confirm the spec ceiling: each intended behavior change must satisfy an acceptance criterion or be necessary support for one. Explicit non-goals remain out of scope.
If the implementation needs behavior outside that ceiling, stop and renegotiate or update the spec before making that expansion.
Make the minimum useful change.
Run relevant verification.
Run the scope gate before declaring the slice complete when SCOPE.md and the helper exist:
```
python scripts/scope_gate.py --base <frozen-base>
```
A scope-gate FAIL blocks completion and requires a revert or pre-write scope renegotiation. REVIEW_REQUIRED must be surfaced and resolved; it is not permission to continue silently.
Update VERIFY.md or HANDOFF.md with a compact build note:
- Selected slice
- Files touched
- Why each file was touched
- Compatibility seams preserved
- Analysis checkpoint: FRESH | NOT_NEEDED
- Scope gate: PASS | FAIL | REVIEW_REQUIRED
- Spec ceiling respected: yes/no
- Unexpected behavior added: none | describe
- Tests changed: yes/no
- Verification run
- Stop reason
Update task status.
Stop after one task.
Summarize changed files and result.

Read the full file on GitHub · 92 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.

10d ago First seen · 92 lines · 27 tokens per session scan A c798b3c9ab8a

Subscribe to this mod's changes

build-one is a skill published in the GitHub repository tmusser/ai-engineering-skills (4 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 892 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.

Claude Code Planning agent-skills agentic-workflows ai-assisted-coding ai-engineering coding-agents

awsl

Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.

XhinLiang/awsl · 63 tokens

dwi-all-in-one

Apply the relevant Dwi lenses together when several observed workflow problems co-occur. Select only the lenses the task needs, preserve a silent fast path for clear reversible work, and keep authority and evidence explicit. Prefer a focused module when one issue dominates.

thienhoc/dwi-by-thienhoc · 56 tokens

dwi-arc

Structure genuinely multi-agent coding work into bounded cells with one writer per scope, explicit integration, and independent review. Use when several disjoint workstreams justify coordination. Do not use for small tasks, overlapping writers, speculative agent fleets, or process artifacts without demonstrated value.

thienhoc/dwi-by-thienhoc · 58 tokens

dwi-bridge

Coordinate bounded work between native Claude and Codex workflows with explicit authority, scope, and evidence. Use for read-only consultation or explicitly authorized execution delegation. Do not create a new connector, share secrets, treat messages as authorization, or allow recursive delegation.

thienhoc/dwi-by-thienhoc · 55 tokens

dwi-budget

Set and report practical token, context, time, tool-call, and coordination boundaries for coding-agent work. Use when resource use is unclear or needs a checkpoint. Do not invent measurements, monetary savings, cache benefit, or precision that the harness does not expose.