project-specs-implementation

A skill for implementing code changes from already-agreed project specifications, such as PRDs, ADRs, acceptance scenarios, or an implementation handoff. It connects those requirements to tests and the resulting code.

In plain words
What is it for?
It helps map acceptance scenarios to tests, implement the requested behavior, preserve links between requirements and tests, and report verification results.
Why use it?
It prevents implementation from quietly inventing requirements and helps verify that the delivered change matches the governing specifications. If the requirements are incomplete or contradictory, it sends the work back for clarification in the specification stage.

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/leefowlercu/agent-kit/project-specs-implementation
Any agent
npx skills add leefowlercu/agent-kit --skill project-specs-implementation
Clone the repo
git clone --depth 1 https://github.com/leefowlercu/agent-kit

Made for: Claude Code, Codex.

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,298 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 $0.00101 $0.01298
Opus 5 $0.00051 $0.00649
Sonnet 5 $0.00020 $0.00260
Haiku 4.5 $0.00010 $0.00130

Measured yesterday against content hash 184ba5f1f198, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-specs-implementation 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.

plugins/spec-governed-development/skills/project-specs-implementation/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Specs Implementation

Use this skill to implement a project change after the governing PRD or ADR has been reconciled. Consume the implementation_handoff from project-specs-reconciliation when available.

Do not use this skill to invent or rewrite product requirements. If the requested behavior is not covered by a reconciled PRD, ADR, traceability matrix, or explicit user-provided handoff, stop and use project-specs-reconciliation first.

Composition Contract

This skill owns:

  • consuming the reconciled spec handoff
  • mapping PRD acceptance scenarios to executable tests
  • preserving PRD, matrix, Gherkin, and test traceability
  • sequencing implementation through governance red, implementation red, green, refactor, and verification
  • reporting implementation results back against the governing specs

Use language-specific or repository-specific skills for:

  • test framework idioms
  • fixture and mock patterns
  • exact red-green-refactor mechanics
  • package, module, or command layout
  • style and lint conventions
  • build, run, and debugger workflows

Treat the workflow as two red phases:

governance red: reconciled PRD, ADR, matrix, or handoff exists before code changes
implementation red: executable acceptance, integration, or unit tests fail for the intended behavior

Stage 1: Confirm Governance Inputs

Step 1: Read local instructions

Read applicable local instructions before changing code. Prefer nearer-scope repository guidance over this skill when they conflict.

Step 2: Locate the governing specs

Use the paths from the implementation_handoff when present. Otherwise use the conventional locations from project-specs-reconciliation:

docs/PRD/
docs/ADR/
docs/<scope>/PRD/
docs/<scope>/ADR/

Read only the relevant PRDs, ADRs, README.md indexes, and MATRIX.md files needed to understand the requested implementation.

Step 3: Check for a valid handoff

Confirm the implementation has:

  • a behavior owner
  • relevant PRD or ADR paths
  • acceptance scenarios or explicit verification expectations
  • expected red tests or a clear reason no new test is needed
  • implementation constraints

Read the full file on GitHub · 152 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 152 lines · 101 tokens per session scan A 184ba5f1f198

Subscribe to this mod's changes

project-specs-implementation is a skill published in the GitHub repository leefowlercu/agent-kit (6 stars, last pushed 29d ago), licensed MIT. It adds 101 tokens to every session and 1,298 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens