build-agent
Skill0 starsChanged 4 months agoMITView on GitHub
Create a single AI agent definition file. Use when adding an agent to an existing team, creating a specialist, defining a new role, or expanding a division.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- moveo-ai/agent-skillstheir own version, first seen Nov 15, 2026
- Happy-Technologies-LLC/happy-platform-skillstheir own version, first seen Nov 1, 2026
- Big-LAORE/Biblioth-que-de-skillstheir own version, first seen Nov 1, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
- duyet/clickhouse-monitoringtheir own version, first seen Oct 8, 2026
- anayatkhan1/kittheir own version, first seen Jul 27, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- anthropics/knowledge-work-plugins★ 36ksame name
- LukeRenton/explore-claude-code★ 329same name
- duyet/clickhouse-monitoring★ 305same name
- Agile-V/agile_v_skills★ 54same name
- Happy-Technologies-LLC/happy-platform-skills★ 41same name
- anayatkhan1/kit★ 16same name
- Big-LAORE/Biblioth-que-de-skills★ 1same name
- moveo-ai/agent-skills★ 1same name
- schift-io/skills★ 1same name
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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-teamSkill
- build-pipelineSkill
- build-skillSkill
- build-teamSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
16 rules. 0 are common, 11 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read research/agent-architecture-playbook.md sections 2 (Agent Definition Template), 3 (Specialization Design), and 6 (Memory Architecture) …
- Very specific: line 14
Read standards/floor-spec.md §2 — agent-file requirements: frontmatter with name, description, explicit model tier.
- Distinctive: line 23
Tools: Read, Write, Edit, Grep, Glob, Bash, WebSearch, WebFetch, Agent?
- Distinctive: line 37
If the agent spawns other agents or makes kill/advance decisions: opus
- Distinctive: line 38
If the agent does substantive domain work (analysis, writing, code): sonnet
- Distinctive: line 39
If the agent does mechanical transformation with no judgment: haiku
- Distinctive: line 40
If uncertain: sonnet (safe default, upgrade to opus if quality issues emerge)
- Very specific: line 44
Write the agent .md file using templates/agent-definition.md as the base:
- Distinctive: line 68
No two agents write the same files.
- Distinctive: line 86
Update board, post results, backward propagation on failure.
- Distinctive: line 90
When this agent is spawned by an orchestrator, the spawn prompt MUST include:
- Distinctive: line 121
After writing the agent .md file, update the team workspace so the new agent is discoverable:
- Distinctive: line 123
Team roster: Add the agent to the roster table in the team's CLAUDE.md (row: role, spawn wave, tools, special authority).
- Very specific: line 124
Spawn order: If the team has a spawn order (Wave 1/2/3), slot the new agent into the right wave and note why.
- Very specific: line 125
File ownership audit: Read every other agent in .claude/agents/ and confirm no path in this agent's "Files Owned" overlaps with another …
- Distinctive: line 126
Routing updates: If the team's CLAUDE.md has a "Routing" section, add any request types this new agent owns.
“Common” is measured: kept by at least 6 in 10 of the 9 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
Build Agent
Trigger
"Add an agent", "create a [role] agent", "I need a [specialist] for [team]", "expand [division] with a new role", "define an agent for [task]".
Research (Read Before Building)
- Read
research/agent-architecture-playbook.mdsections 2 (Agent Definition Template), 3 (Specialization Design), and 6 (Memory Architecture) for agent design patterns and anti-patterns. - Read
standards/floor-spec.md§2 — agent-file requirements: frontmatter withname,description, explicit model tier; exactly one authority tier (ADVISORY / COMMIT / BLOCK / VETO / HALT); Files Owned with no two agents owning the same path; dependency map; ≥3 autonomous failure triggers; On Completion postbacks.
Intake
Ask:
- Role name: What is this agent called? (kebab-case, e.g., "contract-reviewer", "qa-engineer")
- Division: Which team does it belong to?
- Mandate: One sentence: what is this agent's job?
- Model tier: See Model Selection below. Default: sonnet for specialists, opus for managers/orchestrators.
- Tools: Read, Write, Edit, Grep, Glob, Bash, WebSearch, WebFetch, Agent? Red team = disallow Write/Edit.
- Files owned: What files does this agent create/modify? (No overlap with other agents.)
- Feeds from / feeds to: Who gives it work? Who receives its output?
- Special authority: exactly one tier from the Floor Spec v2 ladder — ADVISORY / COMMIT / BLOCK / VETO / HALT. Read-only (red team)?
Model Selection Framework
| Tier | Model | Use When | Cost/Speed |
| Orchestrator | opus | Makes judgment calls, resolves disputes, owns pipeline state, spawns other agents | Highest cost, highest quality |
| Specialist | sonnet | Domain work: writing, analysis, code, review. Most agents are here. | Mid cost, fast |
| Utility | haiku | High-volume, low-judgment tasks: formatting, extraction, classification, routing | Lowest cost, fastest |
Decision rules:
- If the agent spawns other agents or makes kill/advance decisions: opus
- If the agent does substantive domain work (analysis, writing, code): sonnet
- If the agent does mechanical transformation with no judgment: haiku
- If uncertain: sonnet (safe default, upgrade to opus if quality issues emerge)
Generate
Write the agent .md file using templates/agent-definition.md as the base:
---
name: [role-name]
description: [One-line description of role and primary output]
model: [opus|sonnet|haiku]
tools:
- Read
- Write
- Edit
- Grep
- Glob
- Bash
disallowedTools: [] # [Write, Edit, Bash] for red team / read-only agents
---Mandatory Sections
1. Identity and Mandate (2-3 sentences) Who you are, what you protect, your core operating principle.
2. Files Owned (explicit paths) No two agents write the same files. If shared files exist, define a coordination protocol.
3. Key Context (3-5 domain constraints) Critical knowledge the agent needs. Known pitfalls. Quality thresholds.
4. First Action (numbered spawn checklist) Exactly what to read before doing anything: division CLAUDE.md, memory, wire, board, inbox.
5. Autonomous Failure Triggers (pre-work checks) Conditions to check BEFORE starting assigned work. If any fire, report immediately.
6. Dependency Map (upstream, downstream, parallel) Who feeds this agent. Who consumes its output. Who runs concurrently.
7. Output Format (structured) DIVISION, TASK, STATUS, RESULT, ARTIFACTS, ESCALATION. Consistent format enables automated parsing.
8. On Completion (post-work checklist) Update board, post results, backward propagation on failure.
Spawn Prompt Pattern
When this agent is spawned by an orchestrator, the spawn prompt MUST include:
[AGENT NAME]: [SPECIFIC TASK with exact file paths].
Context: [What you need to know about current state].
Input: [Exact file path or data to read].
Output: [Exact file path to write, format expected].
Priority: [P1/P2/P3].
Done when: [Specific, verifiable completion criteria].BAD: "Alpha, work on signals."
GOOD (multi-division team): "Signal Architect: derive 3 novel direction signals from cross-asset momentum literature. Read divisions/alpha-research/memory/MEMORY.md for existing signals (avoid duplication) and research/decision-engine.md for the signal specification schema. Output to divisions/alpha-research/outbox/2026-04-15-signals.md. P2. Done when 3 signals have mathematical specification, expected frequency estimate, and ExitProfile recommendation."
GOOD (single-team): "QA Engineer: expand regression coverage on the public API endpoints. Read memory/MEMORY.md for known edge cases and comms/board.md for the current endpoint list. Output test plan to outbox/2026-04-18-api-regression-plan.md and new tests to tests/integration/api/. P1. Done when every public endpoint has at least one happy-path and one failure-path test, and CI is green."
Quality Checks
- Mandate is specific (not "help with things" or "assist the team")
- File ownership is explicit (no shared ownership without coordination protocol)
- First Action reads team/division memory (institutional knowledge prevents repeated mistakes)
- Dependency map has both upstream and downstream (orphaned agents are useless agents)
- Output format is structured (not free text -- consumers need parseable output)
- Red team agents have Write/Edit/Bash in disallowedTools (separation of creation from critique)
- Autonomous failure triggers are domain-specific (not generic placeholders)
- Model tier matches the judgment requirements of the role
- Paths match the team's structure: multi-division uses
divisions/[name]/memory/anddivisions/[name]/outbox/; single-team usesmemory/andoutbox/at root
Post-Generation (Mandatory)
After writing the agent .md file, update the team workspace so the new agent is discoverable:
- Team roster: Add the agent to the roster table in the team's
CLAUDE.md(row: role, spawn wave, tools, special authority). - Spawn order: If the team has a spawn order (Wave 1/2/3), slot the new agent into the right wave and note why.
- File ownership audit: Read every other agent in
.claude/agents/and confirm no path in this agent's "Files Owned" overlaps with another agent's ownership. If overlap exists, resolve it before declaring done. - Routing updates: If the team's
CLAUDE.mdhas a "Routing" section, add any request types this new agent owns. - Channel post: Post a handoff note to
comms/channels/[team-domain].mdannouncing the new agent and what it owns.
A new agent isn't "added" until the workspace knows about it. Skipping these steps produces orphan agents.
Parallel Fan-Out Note
For any multi-item batch (N ≥ 2 posts, audits, reviews, analyses, cleanups), spawn one top-level agent per item, running in parallel, rather than routing the batch through a single orchestrator that processes items serially or via internal sub-agents invisible to the user.
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.

