An implementation workflow for carrying out an approved plan for a substantial code change. It coordinates dependent tasks and records what was done and how it was checked.

Use it after a plan is approved to build the change, run independent review and exercise checks, measure the result, and stop before committing or publishing automatically.

It gives large changes a controlled path from an approved plan through implementation, review, behavior checks, and a final human decision to ship.

craft — Skill for Claude Code and Codex by brolag: An implementation workflow for carrying out an approved plan…

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 skills/brolag/neural-claude-code/craft

Any agent

npx skills add brolag/neural-claude-code --skill craft

Clone the repo

git clone --depth 1 https://github.com/brolag/neural-claude-code

Made for: Claude Code, Codex.

Or install neural, the plugin that ships this one along with the rest of its 9 skills, 3 hooks.

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/brolag/neural-claude-code/craft.svg)](https://agentmods.dev/skills/brolag/neural-claude-code/craft)

Your own site

<a href="https://agentmods.dev/skills/brolag/neural-claude-code/craft"><img src="https://agentmods.dev/badge/skills/brolag/neural-claude-code/craft.svg" alt="Measured on agentmods" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,169 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.

Model	Per session	Once invoked
Fable 5	$0.00071	$0.01169
Opus 5	$0.00036	$0.00584
Sonnet 5	$0.00014	$0.00234
Haiku 4.5	$0.00007	$0.00117

Measured 3d ago against content hash 44e02188be47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

craft 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 3d 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/craft/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Craft

Execute an approved plan into verified work. Planning belongs to /spec. Review and behavior remain independent gates.

This skill is the Claude Code port of the Neural Codex craft gate. Same contract, slash invocation. Parallel work uses the native Agent tool. No external model pool is required.

1. Resolve and approve the plan

Use an explicit plan path when supplied. Otherwise select the newest related plans/**/plan.md.

Before reading or writing beside the plan, resolve the repository root, the repository's plans/ directory, and the candidate file. Require os.path.commonpath([candidate, plans_root]) == plans_root, require a regular plan.md-style Markdown file, and reject symlinks that leave plans/. Reject ../../outside/plan.md, plans/../outside/plan.md, /tmp/external-plan.md, and any equivalent traversal. Only after this check may baseline.md or evidence be written beside the plan.

If no plan exists and the change is still poorly understood, run /discover first. Otherwise run /spec, get approval, then continue.

Proceed only when:

frontmatter is status: approved, or
the user explicitly invokes /craft immediately after reviewing a specific draft, which counts as approval and must be recorded in the Amend log.

If the plan is missing, stale, blocked, or still ambiguous, stop and return to /spec. Validate that locked signatures still match the repository and the [needs:] graph is complete and acyclic. Inherit references from a sibling unknowns-map.md when one exists.

2. Capture the baseline before edits

Write baseline.md beside the plan. Record:

branch, base commit, and pre-existing dirty files
test pass/fail count and warnings
lint, typecheck, coverage, documentation, or performance measures that apply
unavailable metrics as n/a with a reason
the observable before-state the change intends to improve

Never overwrite or discard user changes. If overlapping dirty work makes the build unsafe, stop with exact paths.

Read the full file on GitHub · 96 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.

3d ago First seen · 96 lines · 71 tokens per session scan A 44e02188be47

Subscribe to this mod's changes

craft is a skill published in the GitHub repository brolag/neural-claude-code (11 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 1,169 once invoked, about $0.0004 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.

Planning Project management

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens