agentleFS
Sign inStart free
Thanarak-qThanarak-q/graph-engineering-workflow/adapters/claude.md

graph-engineering-workflow / adapters

CLAUDE.md7 starsChanged 3 months agoMITView on GitHub

Use this package as the provider-neutral graph-engineering-workflow skill for Claude. Trigger for coding work that benefits from independent implementation, research, verification, auditing, merging, or targeted repair loops. If the Claude environment supports a skill directory, expose this package's SKILL.md as the primary instruction file. If the environment uses project instructions instead, copy or reference the core workflow from SKILL.md. Install the whole directory either way — SKILL.md loads ../references/ on demand. - Workers: use native subagents, teams, or isolated worktrees…

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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
  1. Very specific:

    Use this package as the provider-neutral graph-engineering-workflow skill for Claude.

    line 3
  2. Distinctive:

    Keep provider-specific instructions in this file.

    line 9
  3. Very specific:

    If the Claude environment supports a skill directory, expose this package's SKILL.md as the primary instruction file.

    line 15
  4. Distinctive:

    Workers: use native subagents, teams, or isolated worktrees when available.

    line 19
  5. Distinctive:

    No eval case has been run on this host.

    line 34

≈ “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

Graph Engineering Workflow adapter for Claude

Use this package as the provider-neutral graph-engineering-workflow skill for Claude.

Loading

  1. Read ../SKILL.md first.
  2. Apply the workflow, evidence standards, merge rules, safety boundaries, and response format in SKILL.md.
  3. Keep provider-specific instructions in this file; do not duplicate graph guidance.

Invocation

Trigger for coding work that benefits from independent implementation, research, verification, auditing, merging, or targeted repair loops.

If the Claude environment supports a skill directory, expose this package's SKILL.md as the primary instruction file. If the environment uses project instructions instead, copy or reference the core workflow from SKILL.md. Install the whole directory either way — SKILL.md loads ../references/ on demand.

Execution

  • Workers: use native subagents, teams, or isolated worktrees when available.
  • Isolation: give concurrent writers separate worktrees or branches.
  • Grader: a subagent or worktree-scoped session holding the rubric, artifacts, diff, and run record — never the build transcript. Where no separate context is available, record acceptance.grader: self_graded.
  • Clarification: present a short numbered choice list and accept a typed answer.

Collect structured reports before merging, and keep verifier context separate from executor context.

Portability Rules

See README.md for the rules every adapter inherits.

Not yet verified

No eval case has been run on this host. These are loading and mapping notes, not observed behavior.

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