implement

A workflow for carrying out a large software change, with optional planning and code review by other agents.

In plain words
What is it for?
Implement substantial code changes, coordinate implementation agents, review plans, and check completed code.
Why use it?
It helps decide when a change needs a written plan or independent review instead of treating every task the same way.

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

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 843 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 $0.00027 $0.00843
Opus 5 $0.00014 $0.00421
Sonnet 5 $0.00005 $0.00169
Haiku 4.5 $0.00003 $0.00084

Measured 2d ago against content hash 2f80cb012bf3, 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 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 2d 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.

internal/templates/skills/implement/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

implement

Inputs

Require a task, request, or spec as <input> and dispatch targets named implementer, plan_reviewers, and code_reviewer. Providing a target does not imply its use. Do not infer missing targets. Use /dispatch-agent for every dispatch.

Decide Implementation Approach

Inspect the relevant architecture. Reuse existing code and established patterns when they fit <input>. Resolve substantive requirements and tradeoffs before implementation.

Planning and independent review add significant cost. Before implementation, answer each question yes or no:

  • Is a written plan required to confidently complete and verify <input>?
  • If a plan is required, does its material risk or complexity justify independent plan review?
  • Does the implementation's material risk or complexity justify independent code review, whether implementation is direct or planned?

If no plan is required, implement <input> directly without dispatching or writing a plan. Run only targeted checks as needed. Check completion against <input>, resolve gaps until implementation is complete. Then continue to the Finish section.

Implementation with a Written Plan

If a plan is required, write the following self-contained artifacts. Set <run-id> to YYYYMMDD-HHMMSS-<short-rand>:

  • .agent-layer/tmp/write-plan.<run-id>.plan.md - the implementation plan
  • .agent-layer/tmp/write-plan.<run-id>.task.md - a checklist for all requirements, used to assess completion
  • .agent-layer/tmp/write-plan.<run-id>.context.md - all background and context required for executing the implementation plan

If independent plan review is required, write each reviewer a self-contained prompt instructing it to review the plan artifacts against <input> without editing files or implementing. Dispatch all plan_reviewers concurrently. Then update the artifacts to address any findings you agree with that are within <input>'s scope. Do not repeat plan review.

Finally, dispatch implementer with a prompt instructing it to implement the plan from the artifacts, run only targeted checks as needed, and return only after completing the plan. The prompt must also instruct it not to invoke the implement skill or dispatch another implementer.

Read the full file on GitHub · 90 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. 2d ago First seen · 90 lines · 27 tokens per session scan A 2f80cb012bf3

Subscribe to this mod's changes

implement is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 843 once invoked, about $0.0001 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