walkpod1007 GitHub avatar

claude-project-ops

walkpod1007

A portable operating system of rules extracted from a real multi-agent deployment, allowing mid-tier models to replicate the judgment of a top-tier model (Claude Fable 5) via concrete, executable prompts and decision tests.

Stars

74

7-day growth

No data

Forks

7

Open issues

0

License

No data

Last updated

2026-07-04

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It is not a theoretical template but a floor plan traced from a live deployment, with every worked example coming from real incidents and a v1.1 revision based on actual model execution that caught three gaps missed in review.

Who it is for

  • Developers using Claude Code or similar harnesses
  • Teams deploying multi-agent AI systems
  • Engineers wanting to preserve high-tier model behavior after deprecation
  • Operators of long-running AI-assisted projects

Use cases

  • Boosting a mid-tier model (Opus, Sonnet, Haiku) to operate with Fable-level discipline
  • Standardizing agent dispatch, escalation, and verification in a project
  • Capturing and transferring institutional knowledge from a soon-to-be-sunset model
  • Documenting and evolving operational rules with a pitfall log and maintenance process

Strengths

  • Proven in a real cross-machine deployment with dated, de-identified incident examples
  • Designed to run on weak models without frontier-tier dependence
  • Includes explicit exit paths for taste calls and ambiguous problems
  • Built to evolve via lessons.md and a safe revision process

Considerations

  • Does not solve taste and ambiguous problem definition; honest escalation is required
  • Environment-specific facts (model IDs, tool names) must be re-verified in each new deployment
  • Initial adaptation effort needed to adjust generic rules to a specific project context

README quick start

project-ops-template

Keep the Fable state after Fable is gone.

Claude Fable 5 — the top judgment tier — sunsets for subscription use on 2026-07-07. The point of this repo is to capture that judgment as portable doctrine: a rules layer that guides a mid-tier model (Opus, Sonnet-class, even Haiku-class) into operating at the Fable level — knowing when to delegate, when to escalate, when to stop and ask, how to verify without lying to itself, and how the rules themselves get safely revised over time.

You lose the model. You keep the operating discipline that made it good. That transfer — top-tier judgment → concrete, executable rules a lesser model can run — is the whole idea, and it's why the rules are written concrete-to-the-point-of-executable, every one with a decision test and worked examples.

Works with Claude Code, or any harness built around a CLAUDE.md-style entry file plus a subagent/dispatch mechanism.

Why this one, and not a prompt-generated template

This is not a set of rules an LLM was asked to draft in one pass and never ran. It is the operating manual of an actual long-running multi-agent deployment, extracted, sanitized, and open-sourced.

The concrete difference: after the first full version was written, the strongest model available in that deployment was handed the eight-step command loop and told to run it, for real, against a real task — not to review it, to use it. It came back and, in its own words, patched three concrete gaps the desk-review pass had missed (a role-assignment ambiguity, a missing "worker lane" for delegated subtasks, and a fuzzy test for telling a genuine limitation from an excuse). That's the v1.1 revision baked into these files. The rules have also since been the actual dispatch backbone for a real cross-machine deployment and ongoing multi-agent collaboration — every worked example in ops/00-command-loop.md and ops/50-diagnosis.md is a dated, real incident with the identifying details removed, not a hypothetical.

Put simply: most templates are a blueprint. This one is a floor plan traced from a house people actually live in — the floorboards that creak are marked, because someone found them by stepping on them.

What's in the box

project-ops-template/
├── README.md                  ← this file (safe to delete after deployment)
├── CLAUDE.md.template         ← a lean, routing-only CLA

Description

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real deployments, not one-shot generated.

Related repositories

Similar projects matched by category, topics, and programming language.

S40911120
Featured
S40911120 GitHub avatar

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI & Machine LearningLarge Language Models
67
0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI & Machine LearningLarge Language Models
577
bjan
Featured
bjan GitHub avatar

claudemux

Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.

AI & Machine LearningAI Agents
9