github-template-ai-agents
CLAUDE.md2 starsChanged 9 days agoMITView on GitHub
Sub-agent definitions live in .claude/agents/. Each is a Markdown file with YAML frontmatter (name, description, tools, model). Default agents in this template: - agent-creator - scaffold new sub-agent definitions - goap-agent - goal-oriented action planning for complex workflows - loop-agent - iterative refinement loops - analysis-swarm - parallel multi-perspective code analysis Delegate context-heavy research to sub-agents to keep the parent session focused. Follow the shared retrieval → planning → implementation → verification order; use orchestration only when the task needs…
In this repository63 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/avoid-ai-writing/AGENTS.mdAGENTS.md
- .agents/skills/do-web-doc-resolver/AGENTS.mdAGENTS.md
- .agents/skills/skill-evaluator/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- accessibility-auditorSkill
- agent-browserSkill
- agentic-abstentionSkill
- agents-mdSkill
- api-design-firstSkill
- architecture-diagramSkill
- avoid-ai-writingSkill
- cicd-pipelineSkill
- cloudflare-worker-apiSkill
- codacySkill
- codeberg-apiSkill
- code-review-assistantSkill
- css-render-performanceSkill
- database-devopsSkill
- debuggerSkill
- delegateSkill
- dependency-upgradesSkill
- dist-channel-selectionSkill
- docs-hookSkill
- document-rendering-and-locatorsSkill
- dogfoodSkill
- dora-reportSkill
- do-web-doc-resolverSkill
- durable-objectsSkill
- eu-ai-act-complianceSkill
- git-github-workflowSkill
- goap-agentSkill
- implementerSkill
- intent-classifierSkill
- iterative-refinementSkill
- jules-delegatorSkill
- learnSkill
- lifecycle-managementSkill
- local-context-sanitizationSkill
- memory-contextSkill
- migration-refactoringSkill
- nested-build-isolationSkill
- privacy-firstSkill
- progressive-deliverySkill
- pwa-offline-syncSkill
- reader-ui-uxSkill
- readme-best-practicesSkill
- secrets-managementSkill
- secure-invite-and-accessSkill
- security-code-auditorSkill
- shell-script-qualitySkill
- skill-creatorSkill
- skill-evaluatorSkill
- static-analysisSkill
- testing-strategySkill
- test-runnerSkill
- triz-solverSkill
- turso-dbSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Default agents in this template:
- Very specific: line 19
Follow the shared retrieval → planning → implementation → verification order.
- Very specific: line 53
Use /clear between unrelated tasks
- Very specific: line 54
Use Glob/Grep to find code instead of reading whole file trees
- Distinctive: line 55
Prefer sub-agents for multi-step research tasks
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
@AGENTS.md
<!-- Claude Code-specific instructions only. Do not duplicate content from AGENTS.md. -->Claude Code Features
Sub-Agents
Sub-agent definitions live in .claude/agents/. Each is a Markdown file with YAML
frontmatter (name, description, tools, model).
Default agents in this template:
agent-creator- scaffold new sub-agent definitionsgoap-agent- goal-oriented action planning for complex workflowsloop-agent- iterative refinement loopsanalysis-swarm- parallel multi-perspective code analysis
Delegate context-heavy research to sub-agents to keep the parent session focused.
Follow the shared retrieval → planning → implementation → verification order;
use orchestration only when the task needs it. See agents-docs/SUB-AGENTS.md.
Skills
Skills live canonically in .agents/skills/. The .claude/skills/ folder contains
only symlinks. Run ./scripts/setup-skills.sh once after cloning.
Skills use progressive disclosure - SKILL.md is injected only when the agent
decides the skill is needed. Do not pre-load all skills at session start.
See agents-docs/SKILLS.md.
Custom Commands
Project slash commands live in .claude/commands/. Use them for repeatable workflows.
Verification Hooks
Verification hooks run automatically on agent stop events.
- Exit
0= silent success (nothing extra enters context) - Exit
2= errors surfaced to agent, forcing remediation before finishing Seeagents-docs/HOOKS.md. A successful hook is evidence only for the checks it ran, not proof of agent behavior. Downstream adopters customize hooks for their product. Profile, metrics, and shipping policy come only fromAGENTS.md; Claude Code does not add a separate metrics or automatic publishing requirement.
Headless / CI Mode
claude -p "your prompt" --output-format stream-jsonContext Management
- Use
/clearbetween unrelated tasks - Use
Glob/Grepto find code instead of reading whole file trees - Prefer sub-agents for multi-step research tasks
- See
agents-docs/CONTEXT.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.