implement

A workflow for carrying out an approved software change from its proposal and task files. It implements each task, runs checks, commits the work, and verifies the stated acceptance conditions.

In plain words
What is it for?
Use it when a change folder contains a proposal and tasks, especially when the work must be implemented, validated, committed, and checked against expected behaviour.
Why use it?
It lets a fresh coding session follow a complete written plan without relying on earlier conversation context, while preventing work from starting without the required plan.

Skill for Claude CodeCodex

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/ribeirogab/specwright/implement
Any agent
npx skills add ribeirogab/specwright --skill implement
Clone the repo
git clone --depth 1 https://github.com/ribeirogab/specwright

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,466 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 $0.00079 $0.01466
Opus 5 $0.00039 $0.00733
Sonnet 5 $0.00016 $0.00293
Haiku 4.5 $0.00008 $0.00147

Measured yesterday against content hash 7c2477a2a24f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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. A session that degrades a UI check to `curl` records the capability gap
plugins/sw/skills/implement/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

implement — execute the plan

Take a change folder — proposal.md, tasks.md, and design.md when the scope called for one — and build what they describe. This skill is designed to run cold: a fresh session, a different model, a different host, with no memory of the conversation that produced the plan. Those files are the entire input.

Announce at start: "Implementing the plan."

Locate the change

$ARGUMENTS names a change folder or slug → use it. Otherwise list the changes in .specwright/changes/*/ whose proposal.md says status: pending or in-progress and ask which one; a single candidate may be used directly.

Read every file in the folder completely before touching code. Check out the branch named in tasks.md's branch: frontmatter, creating it from the default branch if it does not exist yet, and set status: in-progress in proposal.md.

A folder with no design.md is not incomplete: a low-scope change carries its constraints in tasks.md and needs nothing more. A missing tasks.md is a stop — the change has no plan yet, and writing one is /sw:plan's job, not this skill's.

Never work on the default branch

After the checkout and before the first commit:

git branch --show-current

If it is main or master — because branch: names it, because the checkout did not happen, or because the frontmatter is blank — stop. Report the branch this change should be on and let the maintainer create it. Do not commit, and do not pick a branch name on their behalf.

This gate runs once, here, and it is the only thing standing between an unattended run and a series of commits on the default branch.

Resume from the checkboxes

The checkboxes in tasks.md are the state. Find the first unticked step and start there — everything above it is done, whoever did it. Never restart a task whose boxes are ticked, and never re-derive progress from the git log; the file is the record.

Before starting, confirm the working tree is clean. Uncommitted work from a previous run is ambiguous: report it and let the maintainer resolve it rather than committing or discarding on their behalf.

Read the full file on GitHub · 135 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 · 135 lines · 79 tokens per session scan A 7c2477a2a24f

Subscribe to this mod's changes

implement is a skill published in the GitHub repository ribeirogab/specwright (3 stars, last pushed 24d ago), licensed MIT. It adds 79 tokens to every session and 1,466 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

review-depth

Decide how much review a change has earned, before reviewing it. Selects quick, standard, or deep from stated signals (reviewable changed lines, directory spread, trust-boundary risk flags, blast radius, documentation-only scope), reports the signal table and the rule that fired, then runs house-review at the selected…

hams-ollo/zen-agent-skills · 180 tokens

doc-sync

Use when code has moved and the documentation may not have, or when a documentation set needs auditing for stale claims. Detects documentation drift by checking prose claims against repository facts, classifies every document as current-state (correctable), contract (report-only, human-owned) or ledger (skipped), and…

hams-ollo/zen-agent-skills · 193 tokens

init-worktracking

Scaffold a portable, agent-optimized spec-driven work-tracking system into the current repository: AGENTS.md (global rules + agent reading protocol), a .tasks/ directory of atomic task files, and (by tier) ROADMAP.md, CHANGELOG.md, a validate.py checker, and thin CLAUDE.md/Cursor/Copilot pointers. Choose a footprint…

hams-ollo/zen-agent-skills · 207 tokens

reconcile-worktrees

Safely consolidate one or more isolated git worktrees (for example left behind by parallel background agents, or from the fix-batch skill) into the main working tree, without committing or merging blindly. Use whenever asked to "reconcile the worktrees", "merge these agent branches", "bring the worktree changes back…

hams-ollo/zen-agent-skills · 161 tokens

verifier-agent

Use before reconciling or landing an implementation to independently verify it against its approved spec and its task's acceptance criteria. Runs the declared verification commands and records each exact outcome, composes the spec-conformance lens so a contract divergence fails the run even when every command passes…

hams-ollo/zen-agent-skills · 166 tokens

spec-author

Use when turning a raw idea, feature request, or bug into a persistent behavioral spec before any tasks or code. Drafts a scenario-based spec (problem, goals, non-goals, constraints, Given/When/Then scenarios with stable S-NNN ids, proposed surface, open questions), composes the spec-quality lens to self-check and…

hams-ollo/zen-agent-skills · 133 tokens