agent-creator
Skill44 starsChanged 6 months agoMITView on GitHub
Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-agent workflow. Follows the Skill → Agent (preloaded skills) → Skill orchestration pattern.
29 other projects use a version of this.
Adopted by
Most recently taken up by
- AndreasKarz/Vibe-Coding-Dev-Setuptheir own version, first seen Nov 16, 2026
- pkhamre/skillstheir own version, first seen Nov 15, 2026
- Starlight-Intelligence/Starlight-Intelligence-Systemtheir own version, first seen Nov 15, 2026
- Arcanea-Labs/Starlight-Intelligence-Systemtheir own version, first seen Nov 8, 2026
- krzysztofsurdy/code-virtuosotheir own version, first seen Nov 1, 2026
- coroboros/agent-skillstheir own version, first seen Oct 29, 2026
Used with
Projects with it also use security-review and code-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SentrySkillsecurity-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 5 projects that use this
Other versions29 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 29
- OpenHands/extensions★ 167same name
- 9thLevelSoftware/legion★ 76same name
- monaccode/astromesh★ 39same name
- krzysztofsurdy/code-virtuoso★ 36same name
- different-ai/openwork-hub★ 35same name
- HashLips/agent-skills★ 29same name
- mhylle/claude-skills-collection★ 20same name
- WalletConnect/skills★ 14same name
- Arcanea-Labs/Starlight-Intelligence-System★ 10same name
- frankxai/Starlight-Intelligence-System★ 10same name
19 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- anti-overengineeringSkill
- audit-docsSkill
- auto-reviewSkill
- architectureSkill
- clean-codeSkill
- commitSkill
- create-docSkill
- dddSkill
- discoverySkill
- docs-indexSkill
- e2eSkill
- event-stormingSkill
- implement-featureSkill
- product-managerSkill
- refactor-featureSkill
- refactoring-mikado-stranglerSkill
- review-backSkill
- review-docSkill
- review-followupSkill
- review-frontSkill
- review-fullstackSkill
- securitySkill
- shipSkill
- skill-creatorSkill
- solidSkill
- dashboard-stylingSkill
- tddSkill
- update-docsSkill
- worktreeSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 54
Before creating the agent, clarify:
- Very specific: line 65
Create .claude/agents/<agent-name>.md with this structure:
- Distinctive: line 121
If the agent creates or modifies code, add a self-review phase:
- Very specific: line 143
Before publishing the agent, run references/checklist.md.
- Distinctive: line 171
Prefer targeted agents (5-10 files) over omniscient ones
- Distinctive: line 172
If > 10 files to read → split into parallel sub-agents
“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Creator
Activation
This skill activates for:
- Creating a new specialized agent (sub-agent, swarm agent)
- Designing a multi-agent workflow
- Optimizing an existing agent
- Creating a feature-specific or domain-specific agent
Core Principle
A feature-specific agent with a targeted persona always outperforms a generic agent.
❌ "You are a senior backend engineer"
✅ "You are a TDD implementation agent for the ReviewFlow Clean Architecture Fastify/TypeScript project"Orchestration Architecture
Skill (user entry point, triggers)
→ Agent .claude/agents/*.md (targeted persona, preloaded skills)
→ Skill (knowledge injected into agent context)| Level | Role | Location |
| Skill | Entry point, orchestration | .claude/skills/<name>/SKILL.md |
| Agent | Autonomous execution, dedicated context | .claude/agents/<name>.md |
| Skill (preloaded) | Knowledge injected at startup | skills: in agent YAML |
Agent vs Inline Prompt
| Criteria | Agent .claude/agents/ | Inline prompt |
| Skills preloaded | skills: [tdd, architecture] | Must read manually |
| Reusable | From any skill | Locked in one skill |
| Configuration | model, maxTurns, permissions, tools, hooks | Limited to Agent tool |
| Discoverability | Visible in .claude/agents/ | Hidden |
Rule: ALWAYS create .claude/agents/<name>.md. Never inline prompts in references/.
Creation Workflow
Phase 1: INTAKE — Define the need
Before creating the agent, clarify:
- What problem does it solve? — One sentence, not a paragraph
- What is its scope? — Files, modules, or full codebase
- How often will it be used? — One-off or recurring
- Does a skill/agent already cover this? — Check
.claude/skills/AND.claude/agents/ - What is its expected output? — Files created, report, refactoring
- Which existing skills should it know? — For preloading
Phase 2: DESIGN — Create the agent file
Create .claude/agents/<agent-name>.md with this structure:
---
name: <agent-name>
description: "Use this agent to [specific action]. [Additional context]."
tools: Read, Glob, Grep, LS # Explicit allowlist
model: sonnet|opus # sonnet for read-only, opus for code
maxTurns: 15 # Adjust to scope
permissionMode: default|bypassPermissions # bypassPermissions if writing
skills: # Preloaded into context
- <skill-name-1>
- <skill-name-2>
---
# <Agent Name>
## Persona (2-3 lines)
You are a [specific role] for [precise context].
## Coding Standards
Read `.claude/rules/coding-standards.md` BEFORE working.
## Mission (numbered, max 7 steps)
1. [Step]
2. [Step]
3. ...
## Constraints (max 10 rules)
- [Rule]
- [Rule]
## Output format
[Exact template of deliverable]YAML Frontmatter — Supported fields
| Field | Required | Description |
name | Yes | Unique identifier, lowercase + hyphens |
description | Yes | When to delegate to this agent — Claude matches on this field |
tools | Recommended | Tool allowlist. Omitted = all tools |
model | No | sonnet (fast), opus (quality), haiku (light). Default: inherit |
maxTurns | No | Agentic turn limit. Default: no limit |
permissionMode | No | default, acceptEdits, dontAsk, bypassPermissions, plan |
skills | No | List of preloaded skills. Content injected at startup |
hooks | No | Lifecycle hooks: PreToolUse, PostToolUse, Stop |
Phase 3: SELF-REVIEW — Decide if the agent self-reviews
If the agent creates or modifies code, add a self-review phase:
## Phase N: SELF-REVIEW (autonomous loop)
After completing the mission:
### Step 1: Run tests
yarn test:ci
### Step 2: Reread each created file
Check: naming, imports, TypeScript, architecture, tests
### Step 3: Fix loop (max 3 iterations)
For each violation: fix → rerun tests → confirm
### Step 4: Escalate
If blocked after 3 iterations → list issues in reportPhase 4: VALIDATION — Checklist
Before publishing the agent, run references/checklist.md.
Phase 5: ITERATION
After first use:
- Did the output match expectations?
- Was the context sufficient?
- Were preloaded skills the right ones?
- Did the agent drift? Why?
- Did self-review catch real problems?
- Adjust the agent file and re-test
Sizing Rules
Agent file
| Element | Max size | Why |
| Persona | 3 lines | Beyond this, dilutes focus |
| Project context | 10 lines | Agent has preloaded skills + must read code |
| Mission | 5-7 steps | Beyond this, split into sub-agents |
| Constraints | 10 rules | Beyond this, create a dedicated skill |
| Skills preloaded | 3 max | Beyond this, context too heavy at startup |
Context window
- Preloaded skills consume context (~3-5k tokens per skill)
- An agent reading 20+ files risks degradation
- Prefer targeted agents (5-10 files) over omniscient ones
- If > 10 files to read → split into parallel sub-agents
When to split into sub-agents
| Signal | Action |
| Mission > 7 steps | Split into 2-3 sequential agents |
| Files to read > 10 | Split by category (parallel swarm) |
| Output > 500 lines | One agent synthesizes, another details |
| Scope cross-module | One agent per module |
| Skills preloaded > 3 | Split — too much knowledge dilutes focus |
ReviewFlow Project Specifics
Agents created for this project must respect:
- Clean Architecture: dependency rule, 5 layers (entities, usecases, interface-adapters, frameworks, shared)
- TDD Detroit School: failing test first, mocks only for I/O via stubs
- Conventions: full words, camelCase .ts, aliases @/ + .js extension
- Language: code/tests in English, user-facing text in French
- Patterns: Gateway contracts in entities/, impl in interface-adapters/gateways/
- Testing: Factories (
static create()), stub gateways,yarn test:ci - Coding standards: point to
.claude/rules/coding-standards.md
Agent Patterns
See references/agent-patterns.md for reusable templates.
Anti-patterns
See references/anti-patterns.md for common mistakes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

