duet-agent: Skill for Claude Code

.agents/skills/implement-spec/SKILL.md

implement-spec is a skill for Claude Code, Codex from dzhng/duet-agent. It costs 41 tokens per session (3,538 once invoked), scanned A, a copy of implement-spec, Apache-2.0.

A workflow for completing a detailed software specification in small, reviewable code changes. Each pass is committed and the next pass continues until the specification is complete.

In plain words
What is it for?
For building multi-step features, coordinating independent work, maintaining checkpoints, and tracking global TODOs and required checks.
Why use it?
It prevents long implementation work from losing track of unfinished parts, stale plans, cleanup, or handoffs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is dzhng/duet-agent's own configuration. It tells Claude Code and Codex how to work on duet-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything duet-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dzhng/duet-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dzhng/duet-agent/main/.agents/skills/implement-spec/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dzhng/duet-agent

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.

agentmods badge for implement-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/dzhng/duet-agent/implement-spec/github.svg)](https://agentmods.dev/skills/dzhng/duet-agent/implement-spec)
Your own site
<a href="https://agentmods.dev/skills/dzhng/duet-agent/implement-spec"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/implement-spec/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.

agentmods 80×15 button for implement-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/dzhng/duet-agent/implement-spec"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/implement-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,538 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 98% copy Near-identical to another mod 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 5.1 $0.00041 $0.03538
Opus 5.5 $0.00016 $0.01415
Sonnet 5.5 $0.00008 $0.00708
Haiku 4.5 $0.00004 $0.00354

Measured 6d ago against content hash c13d61e6c280, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

implement-spec 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 6d 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.

Origin

This is a copy

98% identical to implement-spec — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/implement-spec/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Spec

Build the active spec to completion, one reviewable pass at a time. The spec is the implementation plan; user constraints and accepted experimental evidence remain binding when the architecture changes.

A pass (usually one slice) is a commit checkpoint, not a stopping point. The job is the whole spec — every slice, every global TODO — not the first green commit. Finishing a pass means starting the next one, not handing back to the user. Only stop when the spec is fully implemented (or a genuine blocker needs a decision only the user can make).

Work in parallel wherever the graph allows. Do not walk the ladder one slice at a time when slices are independent. Read the spec's dependency graph as a wavefront and delegate independent passes to subagents that run concurrently (see Rules) — you orchestrate and integrate; only serialize what genuinely depends on prior work.

Workflow

  1. Read the repo README, the spec README, and the next slice before editing. Load any skills named by the spec. Identify the current pickup point, global TODOs, required gates, and what must stay green. If a multi-slice spec lacks a live handoff prompt, add one before the first pass ends. For a validated spike, apply Preserve the winner below before editing.
  2. Reconcile the plan with the current code. If the slice would preserve a development-only shim, duplicated type, weak wrapper, or obsolete path, replace it with the simpler architecture and update the spec handoff.
  3. Implement one coherent pass: usually one slice, one vertical checkpoint, or one architecture correction. Keep the review surface small enough to audit.
  4. Verify the actual contract. For behavior changes, run the focused tests first; for browser-visible work, use the real browser/harness and inspect screenshots so the subject is framed and readable, not merely nonblank. A visual CHANGE carries two extra proofs before you claim it: a byte/pixel diff against the pre-change baseline on the production route (static checks and re-anchored assertions all pass on a no-op — a palette pass once shipped "verified" while the production frame was byte-identical), and an unprimed screenshot-critique — at the user's reported framing when the pass answers their visual bug report — before declaring it fixed; the implementer's eyes are primed by the fix and repeatedly pass what fresh eyes catch. Never weaken an existing default gate or repin a failing contract without proving the old contract is wrong.
  5. Review the change list and clean up after every pass, before committing. Read git status/git diff --stat line by line and account for every path: one-off probes, shot scripts, scratch files, nohup.out, ad-hoc screenshot dirs, and disposable SPIKE/debug notes never enter a commit — scratch stays out of the tree. Preserve frozen references, fixtures, and research evidence in the project's reference or spec assets area. A file without a durable purpose does not ship. Delegated agents leak these; the integrating reviewer re-checks the merged tree with the same eye.

Read the full file on GitHub · 253 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. 6d ago Changed c13d61e6c280
  2. 25d ago Changed · +18 lines f8d5b247b42e
  3. 1mo ago First seen · 235 lines · 41 tokens per session scan A a54b5ffcae40

Subscribe to this mod's changes

implement-spec is a skill published in the GitHub repository dzhng/duet-agent (52 stars, last pushed 7d ago), licensed Apache-2.0. It adds 41 tokens to every session and 3,538 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to implement-spec, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

commit

Generate git commit messages from staged changes.

suyoumo/ClawProBench · 9 tokens

task-stage-report

Apply the stage completion procedure for a Hyper-Waterfall task. Write the stage report (stage{N}.md), commit stage source and report together, and run stage verification commands. Invoke after a stage completes and before entering the next stage.

postmelee/hyper-waterfall · 55 tokens

review-before-commit

Run a behavioral self-check before persisting story results. Verifies diff simplicity, scope adherence, and verifiable completion against enso §10 behavioral principles. Use when a story's implementation is complete and ready to close.

usefulmove/enso · 49 tokens

generator-fix-integrator

Internal Auto-Harness generator skill for worktree-merge fix integration. Use only inside the parallel Generator integrator when it is addressing named defects from QA or retest.

redker56/auto-harness · 40 tokens

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens