scoped-implementation

scoped-implementation is a skill for Claude Code, Codex from darrencroton/ai-agent-coder. It costs 53 tokens per session (708 once invoked), scanned A, original, MIT.

A workflow for implementing one approved part of a software plan without expanding its scope.

In plain words
What is it for?
Use it to execute a frozen implementation slice, run its checks, and report the result for a later authorization review.
Why use it?
It makes the allowed files, acceptance criteria, tests, risks, and rollback path explicit before code is changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/darrencroton/ai-agent-coder/scoped-implementation
Any agent
npx skills add darrencroton/ai-agent-coder --skill scoped-implementation
Clone the repo
git clone --depth 1 https://github.com/darrencroton/ai-agent-coder

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 scoped-implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/scoped-implementation.svg)](https://agentmods.dev/skills/darrencroton/ai-agent-coder/scoped-implementation)
Your own site
<a href="https://agentmods.dev/skills/darrencroton/ai-agent-coder/scoped-implementation"><img src="https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/scoped-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 708 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 5.1 $0.00053 $0.00708
Opus 5 $0.00026 $0.00354
Sonnet 5 $0.00011 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 5d ago against content hash c536146ee2db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scoped-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 5d 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/scoped-implementation/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scoped Implementation

Use this skill when a plan already exists and the job is to implement one narrow slice without redrawing the lane.

Preconditions

Before coding, identify the frozen contract:

  • intended slice
  • acceptance criteria
  • allowed files/functions/components
  • tests allowed or expected to change
  • explicit non-goals
  • risky surfaces and approval status
  • validation plan
  • rollback path

If the contract is missing or too vague, stop after drafting a candidate contract and ask the user to approve it. Do not implement a non-trivial change without an auditable slice.

Workflow

  1. Confirm contract - restate the authorized surface and non-goals briefly.
  2. Check starting state - inspect git status and relevant files. Do not overwrite unrelated user changes.
  3. Implement only the slice - keep edits inside the authorized files/functions. Do not perform opportunistic cleanup.
  4. Validate - run the targeted checks from the contract. Add or update tests when the contract requires it. Then run the lint skill differentially against the slice's starting commit (check --base <ref>) and account for every new finding: fix it inside the authorized surface, or record why it stands. If a fix needs an unauthorized file, stop and report rather than widening the surface. Report an uncovered language as a gap, never as a pass.
  5. Prepare drift audit input - collect the frozen contract, changed files, diff summary, and validation results for the user's next explicit call to the drift-audit skill.
  6. Report receipt - finish with the implementation receipt below. Do not run the drift-audit skill as part of this skill unless the user explicitly calls both skills in the same request.

Delegation

Keep small implementation slices local when delegation would add more prompt/context overhead than value.

Use orchestrator only when it is also explicitly requested or already active for the task. When using it:

  • keep implementation, test execution, Git operations, commits, gate decisions, and final delivery with the Developer
  • use a read-only Reviewer only for investigation, evidence gathering, drift audit, or code review
  • invoke a Reviewer for drift audit only when the user explicitly called drift-audit or explicitly asked to combine implementation and drift audit
  • never let a Reviewer edit files, expand the slice, approve drift, own a gate, commit, or re-delegate
  • give a Reviewer applying drift-audit only the frozen contract, diff, and relevant validation evidence

Read the full file on GitHub · 84 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. 5d ago First seen · 84 lines · 53 tokens per session scan A c536146ee2db

Subscribe to this mod's changes

scoped-implementation is a skill published in the GitHub repository darrencroton/ai-agent-coder (2 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 708 once invoked, about $0.0003 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

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