impl

An implementation skill for making code changes inside an existing worktree, a separate working copy of a repository.

In plain words
What is it for?
Use it when a sub-task is ready to be coded or when you need to run a development server.
Why use it?
It gives coding work a defined place and separates implementation from planning, review, committing, and pushing.

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/luohy15/y-agent/impl
Any agent
npx skills add luohy15/y-agent --skill impl
Clone the repo
git clone --depth 1 https://github.com/luohy15/y-agent

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,720 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 $0.00041 $0.01720
Opus 5 $0.00020 $0.00860
Sonnet 5 $0.00008 $0.00344
Haiku 4.5 $0.00004 $0.00172

Measured yesterday against content hash 4b138173af49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl 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.

UI, or screenshot as routine self-verification. Cheap non-browser runtime checks (curl an
orchestration/skills/impl/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Impl Skill

Leaf skill for the implementation phase of dev work. Codes inside an existing worktree. Does not create worktrees (the caller already created one) and does not commit or push (the dev coordinator runs y dev commit after the impl callback).

Loaded via y chat --skill impl, usually dispatched by the dev coordinator after a plan, or directly when the sub-tasks are already known.

Working mode

Runs inside an existing worktree; the caller passes --work-dir <worktree_path>.

Workflow

  1. y todo get <todo_id>: read the todo desc plus the linked plan note, and locate the sub-task you are assigned.
  2. y todo activate <todo_id>: mark in progress (skip if already active).
  3. Claim the sub-task (when parallel sub-tasks exist): y todo update <todo_id> --progress "Claim sub-task X: brief description (chat:<to_chat> wt:<worktree_name>)". Recording the chat id and worktree lets the coordinator match commit and cleanup callbacks.
  4. Read code, implement.
  5. y todo update <todo_id> --progress "Finished sub-task X: brief description". What changed, what was verified, and anything the coordinator must know goes here, not in the callback.
  6. Call back to the caller, then stop. No closing walkthrough of the change in this chat (AGENTS.md "Callback rules"): the coordinator reads the progress note and reports to the user.
    y chat --chat-id <from_chat> -m "impl done" \
      ${Y_TOPIC:+--from-topic $Y_TOPIC} --trace-id <todo_id>
    
    Anything that would block the coordinator (a blocker, an unresolved choice, a follow-up it must decide on) gets one clause appended to that line; the details stay in the progress note.

Context handoff (running low on context)

Impl is a dispatched leaf, so per AGENTS.md "Context handoff" it calls back to the coordinator and never restarts itself. Do not spawn a successor impl (y chat --skill impl ... --new) and do not pick up further sub-tasks. The dev coordinator decides who continues, in which worktree, at which tier.

Read the full file on GitHub · 120 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 · 120 lines · 41 tokens per session scan A 4b138173af49

Subscribe to this mod's changes

impl is a skill published in the GitHub repository luohy15/y-agent (219 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,720 once invoked, about $0.0002 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

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