implement

A workflow delegates requested coding changes to another Codex agent, which edits files in the current working directory.

In plain words
What is it for?
It can build, fix, refactor, or add code when the user asks Codex to hand the implementation to an agent.
Why use it?
It lets a separate coding agent carry out implementation work while following the requested model and reasoning-effort settings.

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/jeffh/claude-plugins/implement
Any agent
npx skills add jeffh/claude-plugins --skill implement
Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-plugins

Made for: Claude Code, Codex.

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,352 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 $0.00170 $0.01352
Opus 5 $0.00085 $0.00676
Sonnet 5 $0.00034 $0.00270
Haiku 4.5 $0.00017 $0.00135

Measured 2d ago against content hash 07b0578d9d65, 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.

codex/skills/implement/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Implement

Delegate an implementation task to a Codex subagent running GPT 5.6 Sol (or another GPT model the user names). The subagent will edit files in the current working directory.

Choosing the model

The -m flag selects the model. Default to gpt-5.6-sol, but honor any specific model the user asks for:

  • Use gpt-5.6-sol unless the user names a different model.
  • If the user specifies a model — e.g. "run gpt-5.6-terra", "use gpt-5.5-codex", "with the <name> model" — pass that exact string to -m instead. Don't validate or second-guess the name; Codex will error if it's unknown.
  • If they typed /codex:implement --model <name> <task> (or -m <name>), strip that flag from the prompt and use <name> as the model.

Choosing the effort

Reasoning effort is set with -c model_reasoning_effort="<level>". Default to high, but honor any level the user asks for:

  • Use high unless the user names a different level.
  • If the user asks in prose — e.g. "low effort", "medium effort" — substitute that level.
  • If they typed /codex:implement --effort <level> <task>, strip that flag from the prompt and use <level> as the effort.

Everywhere below shows -m gpt-5.6-sol and high effort; substitute the chosen model and effort.

How to invoke

  1. Take the user's prompt (either the args passed to this skill, or the surrounding request if they said "have Codex do X").

  2. Run the Bash tool with:

    codex exec \
      -m gpt-5.6-sol \
      -c model_reasoning_effort="high" \
      -s workspace-write \
      --skip-git-repo-check \
      -C "$PWD" \
      "<PROMPT>"
    
    • -m gpt-5.6-sol — the model; default gpt-5.6-sol, or the model the user named (see Choosing the model).
    • -c model_reasoning_effort="high" — reasoning effort; default high, or the level the user named (see Choosing the effort).
    • -s workspace-write — Codex may write files under the workdir + $TMPDIR; this is the safe default. codex exec runs non-interactively with approval mode never (there is no -a/--ask-for-approval flag), so Codex cannot prompt to escalate — it simply stays within the sandbox. Only switch to --dangerously-bypass-approvals-and-sandbox if the user explicitly asks for autonomous, unsandboxed execution.
    • -C "$PWD" — pin the workspace to Claude's current directory.
    • --skip-git-repo-check — allow running outside a git repo. Drop this if the user's task is git-related.
    • Always set an explicit Bash timeout. Implementation runs are slow and the Bash default (120000 ms / 2 min) will kill Codex mid-run. Pass timeout: 600000 (10 min — the maximum the Bash tool allows) on every codex exec call.
    • If the task is large enough that even 10 minutes may not be enough, run the Bash call with run_in_background: true instead and poll its output rather than blocking — a foreground call cannot exceed the 600000 ms cap.

Read the full file on GitHub · 79 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 · 79 lines · 170 tokens per session scan A 07b0578d9d65

Subscribe to this mod's changes

implement is a skill published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 17d ago), licensed Apache-2.0. It adds 170 tokens to every session and 1,352 once invoked, about $0.0009 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 2026-08-30.

Related

Other skills, from other repositories

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

agentmail

Use when an agent needs AgentMail CLI email inboxes.

NousResearch/hermes-agent · 15 tokens

skill-template

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

muratcankoylan/Agent-Skills-for-Context-Engineering · 24 tokens

Agent Development

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…

anthropics/claude-code · 80 tokens

skill-creator

Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.

yologdev/yoyo-evolve · 46 tokens

subagent-delegation

Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.

toonight/get-shit-done-for-antigravity · 42 tokens