code-subagents

Patterns for sending separate implementation tasks to coding subagents. They explain when tasks can run in parallel, when they must run in order, and how to review and combine their work.

In plain words
What is it for?
Use them to plan and dispatch multiple implementation tasks, assign clear requirements and validation, and integrate completed subagent work.
Why use it?
They help divide independent work without mixing unrelated context or creating conflicts in shared files. Dependent tasks are kept in sequence so each uses the previous result.

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/martinffx/atelier/code-subagents
Any agent
npx skills add martinffx/atelier --skill code-subagents
Clone the repo
git clone --depth 1 https://github.com/martinffx/atelier

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,209 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 $0.00044 $0.01209
Opus 5 $0.00022 $0.00605
Sonnet 5 $0.00009 $0.00242
Haiku 4.5 $0.00004 $0.00121

Measured 2d ago against content hash 717ca98df6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-subagents 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.

skills/code-subagents/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Subagents

Fresh subagent per task. One combined review per completed batch. Parallel when independent, sequential when dependent.

When to Use Subagents

Use when:

  • 2+ independent work items do not share state or files
  • Each work item has explicit requirements, constraints, files, and validation
  • Each problem can be understood without context from the other work items

Don't use when:

  • Tasks are tightly coupled (editing the same files)
  • You need to understand full system state across tasks
  • Failures are related (fixing one might fix others)
  • Exploratory work where the problem isn't well-defined yet

Dispatch Modes

Sequential (dependent tasks)

Tasks with dependencies execute one at a time. Each gets a fresh subagent — no context pollution from previous tasks.

Task 1 (Entity) → review → complete
Task 2 (Repository, depends on T1) → review → complete
Task 3 (Service, depends on T2) → review → complete

Parallel (independent tasks)

Independent tasks dispatch simultaneously. One agent per problem domain.

Task A (auth tests) ──→ review → complete
Task B (billing tests) ──→ review → complete    ← concurrent
Task C (notification tests) ──→ review → complete

Independence check: Would fixing Task A affect Task B? Would they edit the same files? If no to both, dispatch in parallel.

For shared-tree parallel work:

  1. Assign each task an exclusive file list before dispatch
  2. Do not let implementers stage or commit changes
  3. Capture full git status, including untracked files, before and after each task
  4. Capture the task's path-scoped patch and reject changes outside its assigned paths
  5. Run tasks sequentially if their file ownership overlaps or cannot be isolated

Prompt Templates

Use these templates when dispatching subagents. Each template is battle-tested — don't improvise, use them as-is and fill in the variables.

Read the full file on GitHub · 156 lines

Files

What ships with it

2 files 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. 2d ago First seen · 156 lines · 44 tokens per session scan A 717ca98df6d6

Subscribe to this mod's changes

code-subagents is a skill published in the GitHub repository martinffx/atelier (44 stars, last pushed 23d ago), licensed MIT. It adds 44 tokens to every session and 1,209 once invoked, about $0.0002 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.