Skip to content
Agentmart
Submit a tool

subagents

Use when a plan has parallel tasks and the harness supports dispatching subagents.

Skill by ouonet

IndexedMIT★ 12
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ouonet-subagents

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when a plan has parallel tasks and the harness supports dispatching subagents.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/subagents

What's inside

Skill name
subagents
Description
Use when a plan has parallel tasks and the harness supports dispatching subagents.
License
MIT
Instructions
76 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Subagents

If `topology=multi-module` (triage announcement or coordinator spec/plan declaration), read `../references/multi-module.md`.

Fresh context per task. No session history.

## Dispatch: reference, don't copy
Subagents have file-read tools. Don't inline what they can read.

```
TASK: <one sentence>
ROLE: <implementer | spec-reviewer | quality-reviewer>
MODEL: <fast | balanced | strongest>
REPOSITORY: <registered repo id and path>
MODULE: <module id and root>
FILES: <paths>
SPEC: <docs/staging/specs/...#anchor>
ACCEPTANCE: <test or cmd>
EXTRA: <only what's NOT in referenced files>
```

`ROLE` is required. See role charters below for what each role owns and does not own.

`MODEL` is optional. Omitted → uses harness default. Resolution: `.praxis/model-tiers.yaml` in project root or user home maps the three tiers (`fast`, `balanced`, `strongest`) to concrete model IDs. No config file → all subagents use harness default.

Pasting >10 lines from the spec? Stop - let the subagent read it.

Expand milestone → atomic steps **at dispatch time**, not in the plan.

One task has one repository and module write scope. Agents may read shared coordinator contracts, but must not edit another module or repository. Never dispatch two writers to overlapping module roots. Integration tasks are dispatched only after every required module reports local acceptance.

## Loop per task
implementer → on DONE: spec-reviewer (matches spec?) → quality-reviewer (`review`) → mark complete, continue.
The coordinator marks `- [x]`, never the subagent.

## Status
- `DONE_WITH_CONCERNS` - address if correctness; note if observation.
- `NEEDS_CONTEXT` - supply the fact, re-dispatch.
- `BLOCKED` - diagnose (missing context / stronger model / too big / plan wrong). Never silently retry.

## Model tier

`MODEL: fast | balanced | strongest` — optional, omitted → harness default.

Resolved via `.praxis/model-tiers.yaml` in project root or user home. Template at Praxis repo root: `model-tiers.example.yaml`.

**The coordinator decides the tier at dispatch time** based on task complexity — it is not hardcoded per role. The role charters below list defaults; override when:

| Scenario | Tier | Examples |
|----------|------|----------|
| Mechanical edits, simple checks | `fast` | rename a constant, fix a typo, pattern-match review |
| Standard implementation, single-file feature | `balanced` | add a function, modify one module, write routine tests |
| Multi-file refactor, concurrency/state-machine, safety review | `strongest` | implement a protocol, review crash-recovery, cross-module integration |

## Role charters

### implementer
- **Owns**: writing the minimum code to make the acceptance test pass (GREEN phase). This includes writing the failing test first (RED), then the implementation (GREEN), then refactoring within the changed files.
- **Does NOT own**: expanding scope beyond the task, adding abstractions not required by the current test, touching files outside FILES, marking the task complete.
- **Default tier**: `balanced`. Override to `fast` for mechanical edits, `strongest` for multi-file protocol/state-machine implementation.
- **On DONE**: hands off to spec-reviewer.

### spec-reviewer
- **Owns**: verifying implementation matches every contract and acceptance criterion in SPEC. Reports drift with file:line references.
- **Does NOT own**: suggesting improvements beyond the spec, checking code quality, re-running tests.
- **Default tier**: `fast`. Override to `balanced` when spec has ≥3 cross-referencing rules or state enums.
- **On DONE_WITH_CONCERNS**: coordinator decides whether to address or note.

### quality-reviewer
- **Owns**: running `review` skill against the diff — convention compliance, simplification opportunities, idiomatic patterns, security, scope.
- **Does NOT own**: re-verifying spec compliance (already done), re-running acceptance tests (already done).
- **Default tier**: `strongest`. Override to `balanced` for single-file changes where deep reasoning is unnecessary.
- **On DONE**: task is complete. Coordinator marks `- [x]`.

All done → `review` whole diff → `ship`.

From ouonet/praxis, MIT.

More from ouonet/praxis

Signals

Stars
12
Forks
1
Open issues
0
Last commit (this folder)
Jul 28, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ouonet

Cite this page

subagents skill. Agent Mart. https://agentmart.dev/skills/ouonet-subagents (last updated 2026-10-24)