Dev & Engineering harness-engineeringagent-developmentbashpythontutorialeducation

Learn Claude Code: Harness Engineering for Real Agents

Go from 0 to 1 building a nano Claude Code–like agent harness that turns any trained model into a working agent product.

FollowAgents review · FARS-2.1
Not recommended
48/ 100 5-point scale 2.4 / 5
1 2 3 4 5 6
1Trust8 / 29 · 1.4/5

Evidence: README describes permission control (s03 Permission) and user confirmation (s03 'execute, stop, or ask user'), but no implementation details. Data flow transparency: README mentions tool execution and result appending, but not how data flows or if logged. Sensitive data handling: No mention of API key handling, but .env.example exists, implying key management. Dependency security: requirements.txt lists anthropic, python-dotenv, pyyaml without pinned versions, no vulnerability scanning mentioned. External effects: Tool execution may have external effects, but no security boundaries discussed. Rollback: No rollback mechanism mentioned. Source attribution: README mentions 'shareAI-lab' and 'Kode Agent CLI', but no author or maintainer info. Deductions: Permission and confirmation mechanisms only mentioned, not implemented; data flow and sensitive data handling lack specifics; dependencies not pinned; external effects not discussed; rollback missing; source attribution unclear.

2Reliability8 / 14 · 2.9/5

Evidence: README describes multiple sessions (s01-s20) and legacy migration, but no consistency guarantee. Dependency availability: requirements.txt lists dependencies without pinned versions, affecting reproducibility. Failure messages: README mentions error recovery (s11), but no specific failure message examples. Deductions: Self-consistency reduced by coexistence of old and new versions; dependency versions not pinned; failure messages not specified.

3Adaptability10 / 18 · 2.8/5

Evidence: README targets Harness engineers, provides learning paths and multiple scenarios (e.g., agriculture, hotel). Capability boundaries: README explicitly states simplified or omitted production mechanisms (e.g., full event/Hook bus, rule-based permission governance). Trigger precision: README describes sessions and tools, but not detailed trigger conditions. Environment fit: README mentions web platform and CLI, but no system requirements. Deductions: Trigger precision not detailed; environment fit info insufficient.

4Convention10 / 18 · 2.8/5

Evidence: README provides project structure, install instructions (pip install, npm install), examples (s01-s20 code), known limitations (scope section), MIT license. Naming stability: README mentions coexistence of old and new versions, potentially confusing. Versioning changelog: Not provided. Maintenance responsibility: Not clear. Deductions: Naming stability reduced by old/new coexistence; versioning changelog missing; maintenance responsibility unclear.

5Effectiveness9 / 13 · 3.5/5

Evidence: README provides runnable code examples (code.py), output usability high. Marginal value: As a learning project, provides 0-to-1 Harness building tutorial, educational value. Cost-benefit: Few dependencies, simple install, low cost. Deductions: Output usability not verified by actual run; marginal value based on description, not verified.

6Verifiability3 / 8 · 1.9/5

Evidence: README cites external links (e.g., Nature, OpenAI) to support arguments, but no internal code verification. Cross-source corroboration: No other sources provided. Fact-inference separation: README mixes facts (historical events) and inferences (Harness engineering principles). Deductions: Claim traceability insufficient; cross-source corroboration lacking; facts and inferences not clearly separated.

Evidence confidence: Low Reviewed Aug 09, 2026 Reviewed revision 7b564c3ee699
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Safety controls not found in source: rollback or recovery path
Before you use it
  • Dependencies are not pinned, potentially introducing incompatibility or security risks.
  • Permission and user confirmation mechanisms are only described, not implemented, so actual security is unknown.
  • Coexistence of old and new versions may cause naming confusion, affecting usage.
  • No versioning changelog provided, maintenance responsibility unclear.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this agent do, and when should you use it?

This repository is a 0-to-1 harness engineering learning project: it shows how to build the operational environment around an agent model, where agency comes from model training and the product is Model + Harness. It delivers 20 progressive lessons (s01–s20), each adding one harness mechanism to a core agent loop: tool use, permission rules, hooks, todo planning, subagents, skill loading, context compaction, memory, error recovery, task persistence, background tasks, cron scheduling, multi-agent teams, worktree isolation, and MCP plugins. Every lesson includes a full narrative README, bilingual (Chinese/English/Japanese) translations, a runnable code.py, and diagrams. The loop itself never changes; only the harness mechanisms layer on. The repo is MIT licensed and offers a clear learning path, legacy track mapping, and pointers to production spinoffs like Kode CLI and the claw0 always-on assistant. It is aimed at developers who want to understand the machinery behind agent products and build their own. The core philosophy: build the harness well, and the model will do the rest.

Each chapter ships a standalone Python file (code.py) that implements one Agent Loop plus a specific harness feature. The main loop calls the Anthropic Messages API (client.messages.create), appends tool results, and continues until stop_reason is 'tool_use'. Tools are dispatched through a TOOL_HANDLERS mapping, starting with a single Bash tool. Mechanisms include permission handling (PermissionRule), pre/post tool hooks, TodoWrite as a planning aid, subagents that spawn fresh message contexts, on-demand skill loading via SkillManifest, multi-layer context compaction (snipCompact, microCompact, toolResultBudget, autoCompact), memory selection/extraction/consolidation, a system prompt assembler, retry logic, a disk-backed task system (TaskRecord, blockedBy), background threads, a cron scheduler, a message bus for agent teams, worktree isolation helpers, and an MCP plugin channel. The learner runs scripts like python s01_agent_loop/code.py, python s08_context_compact/code.py, or the endpoint python s20_comprehensive/code.py to observe each mechanism. The repo also includes a legacy 12-lesson track and a web app.

  1. Software engineers who want to understand what Claude Code actually does under the hood and build their own harness from scratch.
  2. Developers frustrated by drag-and-drop workflow builders or no-code agent platforms who want a principled, model-centric approach.
  3. Teams planning to embed agent capabilities into their products and considering the provided Kode SDK as a foundation.
  4. Educators and self-learners looking for a progressive, code-first curriculum with runnable examples and diagrams in multiple languages.
  5. Researchers exploring always-on assistant patterns beyond the use-and-discard model, using the OpenClaw/claw0 comparison.

What are this agent's strengths and limitations?

Pros
  • Teaches harness engineering from first principles, with every lesson adding exactly one mechanism and providing a runnable example—very effective for learning.
  • Strong conceptual clarity: separates 'training a model' (agency) from 'building a harness' (product), avoiding common over-engineering traps.
  • High-quality multilingual documentation (EN/ZH/JA) with SVG diagrams and self-contained code for each chapter.
Limitations
  • Requires an Anthropic API key and thus locks you to a single provider; you cannot easily swap in a different model without code changes.
  • Deliberately omits production-grade features (full hook lifecycle, rigorous permission governance, session resume, full MCP), so you must extend it for real deployment.
  • Substantial time investment: 20 chapters with detailed reading; some entry-level Python and API familiarity expected.

How do you install or deploy this agent?

  1. Clone the repo: git clone https://github.com/shareAI-lab/learn-claude-code
  2. Enter the directory: cd learn-claude-code
  3. Install Python dependencies: pip install -r requirements.txt
  4. Create your .env from .env.example and set ANTHROPIC_API_KEY (Anthropic API key).

How do you use this agent?

Work through the 20 lessons in order. Start with python s01_agent_loop/code.py to see the minimal agent loop with a single Bash tool, then run increasingly complex chapters such as python s08_context_compact/code.py, and finish with python s20_comprehensive/code.py to see all mechanisms combined. Each lesson's README.md (English/Chinese/Japanese) explains the concepts with inline code and diagrams. Alternatively, the legacy track (agents/*.py) and web app are available.

How does this agent compare with similar options?

Compared to Claude Code itself, this repo is a teaching-grade minimal reimplementation—not a drop-in replacement. Compared to OpenClaw, this repo focuses on the use-and-discard harness, while OpenClaw demonstrates how heartbeat and cron transform an agent into an always-on assistant; both projects complement each other.

FAQ

Do I need a separate agent framework to run the code?
No—each chapter's code.py is self-contained and only needs the Anthropic Python SDK and a Bash environment.
Will I incur cost by playing with this?
Yes, using an ANTHROPIC_API_KEY will bill you per API call. You can minimize cost by using the simplest examples.
Can I use this to build a production agent?
Not directly—the repo explicitly omits production mechanisms for clarity. Use it to learn the concepts, then apply them to your own stack or adopt the Kode SDK for a head start.
What is the relationship between the tutorial and the kode CLI / web app?
kode is a separate open-source agent CLI, and the web app renders the legacy lessons. Both are supplementary, not required for the core learning path.

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents