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.
npx skills add martinffx/atelier --skill code-subagentsgit clone --depth 1 https://github.com/martinffx/atelierWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/martinffx/atelier/code-subagents)<a href="https://agentmods.dev/skills/martinffx/atelier/code-subagents"><img src="https://agentmods.dev/badge/skills/martinffx/atelier/code-subagents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/martinffx/atelier/code-subagents"><img src="https://agentmods.dev/badge/skills/martinffx/atelier/code-subagents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01375 |
| Opus 5.5 | $0.00023 | $0.00550 |
| Sonnet 5.5 | $0.00012 | $0.00275 |
| Haiku 4.5 | $0.00006 | $0.00137 |
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.
How it starts
The opening of the file, as written. The whole thing — 172 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 (all must hold):
- The design is settled: the plan or
design.mdalready specifies what the file contains (types, signatures, schema, contract, or an existing pattern to copy) - The work item has explicit requirements, owned files, and a validation command
- It does not share files or state with other in-flight work
Prime candidates are new files, scaffolding, boilerplate, and pattern-following edits. Parallelism is a separate question: dispatch two or more eligible items concurrently only when the independence check below passes.
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:
- Assign each task an exclusive file list before dispatch
- Do not let implementers stage or commit changes
- Capture full
git status, including untracked files, before and after each task - Capture the task's path-scoped patch and reject changes outside its assigned paths
- Run tasks sequentially if their file ownership overlaps or cannot be isolated
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.
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.
- 2d ago Changed · +1 lines aef6c0fc5085
- 10d ago Changed · +15 lines · +14 tokens per session bfe8f0d45add
- 1mo ago First seen · 156 lines · 44 tokens per session scan A 717ca98df6d6
code-subagents is a skill published in the GitHub repository martinffx/atelier (48 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,375 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
harbor
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence.…
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
omc-review
Evaluate finished work for defects, risk, and simplification before it ships.
tech-debt-collector
Evidence-gated tech debt and bloat detection. Scouts signals, ranks by materiality, validates by refutation, reports up to 5 findings with actions.
pr-review
Intent-aware map-reduce PR review with CI/CD support, confidence gating, and intelligent comment deduplication.
pr-walkthrough
Generate an evidence-grounded markdown walkthrough for a pull request.