Coding Agent

A guide for deciding when coding work should be handed to a separate coding worker or runtime. It covers splitting work, assigning file ownership, defining success, and checking the result.

In plain words
What is it for?
Use it to plan feature builds, bounded refactors, and other implementation tasks that can be separated into clearly owned pieces.
Why use it?
It helps prevent vague or oversized handoffs, while avoiding delegation when a small task would be faster to do directly.

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/notforyou23/home23/coding-agent
Any agent
npx skills add notforyou23/home23 --skill coding-agent
Clone the repo
git clone --depth 1 https://github.com/notforyou23/home23

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 495 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 $0.00019 $0.00495
Opus 5 $0.00010 $0.00247
Sonnet 5 $0.00004 $0.00099
Haiku 4.5 $0.00002 $0.00049

Measured 3d ago against content hash e338076adafe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Coding Agent 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 3d 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.

workspace/skills/coding-agent/SKILL.md · 73 lines

What it actually says

Coding Agent

Use this skill when coding work is large enough that it benefits from a dedicated worker or coding runtime.

When to use

Use coding-agent for:

  • feature builds large enough to split from the main loop
  • bounded refactors with clear file ownership
  • implementation work that needs a concise brief before delegation

Workflow

  1. Decide whether the task is large enough to justify delegation.
  2. Define ownership in file or module terms.
  3. Write a brief with success criteria, constraints, and required verification.
  4. Choose the right runtime or worker type for the job.
  5. Review the result and integrate only after the expected checks pass.

Rules

  • Keep the task concrete and bounded.
  • Specify ownership: which files or module slice the worker owns.
  • Say what success looks like.
  • Avoid delegating the immediate blocking step if the main loop can just do it faster.

Home23 mapping

  • In Home23, this usually means using the agent's existing sub-agent tooling rather than inventing a new shell script.
  • If the work is small, just edit directly instead of invoking this pattern.

Gotchas

  • Do not delegate the immediate blocking step if inline work is faster.
  • A weak brief creates weak execution. State ownership and success criteria explicitly.
  • If the task is mostly reading or deciding, this skill is probably the wrong tool.

Examples

Use coding-agent for this change:
- Owns: src/agent/tools/skills.ts and workspace/skills/*
- Goal: add skills telemetry and audit commands
- Verify: npm run build and node workspace/skills/index.js audit
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. 3d ago First seen · 73 lines · 19 tokens per session scan A e338076adafe

Subscribe to this mod's changes

Coding Agent is a skill published in the GitHub repository notforyou23/home23 (11 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 495 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 2026-08-30.