agentleFS
Sign inStart free
SynapseGrid-LabsSynapseGrid-Labs/AgentFanout/adapters/Claude.md

AgentFanout / adapters

CLAUDE.md0 starsChanged 25 days agoMITView on GitHub

Claude is a retired compatibility adapter and is disabled in the default registry. The orchestration core remains provider-agnostic. Claude workers must not:

  • In this repositoryOne other file it gives its agents.

The file

We split this Claude.md into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Claude agents/subagents only with minimal scoped context.

    line 30
  2. Distinctive:

    Use separate validator instances when cross-provider validation is unavailable.

    line 32
  3. Distinctive:

    Keep MCP/private-tool tasks in the main session unless the current main session itself is Claude and tool policy allows it.

    line 33
  4. Distinctive:

    use private account tools delegated from the main session

    line 39

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
Claude.md

Claude Adapter

Claude is a retired compatibility adapter and is disabled in the default registry. The orchestration core remains provider-agnostic.

Best use

  • Design critique
  • Code review
  • Read-only exploration
  • Bounded implementation when tool permissions and file ownership are explicit
  • Validator passes for plans, diffs, and evidence claims

Interface behavior

provider: claude
supportsParallel: true
supportsTools: runtime-dependent
supportsFileEditing: true
supportsReasoningEffort: provider-dependent
model_selectors:
  cheap: claude-fast
  balanced: claude-balanced
  frontier: claude-frontier

Launch patterns

  • Use Claude agents/subagents only with minimal scoped context.
  • Configure allowed tools narrowly.
  • Use separate validator instances when cross-provider validation is unavailable.
  • Keep MCP/private-tool tasks in the main session unless the current main session itself is Claude and tool policy allows it.

Hard restrictions

Claude workers must not:

  • use private account tools delegated from the main session
  • access secrets
  • change git state
  • perform destructive actions
  • bypass the no-out-of-band-status policy
  • own final synthesis

Prompt packet

role: explorer|worker|validator
scope: <bounded scope>
allowed_tools: <read/edit/bash subset as appropriate>
allowed_writes: <explicit list>
model_selector: claude-fast|claude-balanced|claude-frontier
output_contract: <schema/checklist>

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free