# sanbuphy/learn-coding-agent

Research on Coding Agents

Repository: https://github.com/sanbuphy/learn-coding-agent
Canonical: https://ross.abutalabs.com/products/learn-coding-agent
License Family: other
Last push: 2026-04-01T10:55:06+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 75, release rhythm 35, longevity 11
- inputs: {"age_days": 155, "days_push": 154, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12245, forks 19568 (observed 2026-08-28T04:10:52.134418+00:00)

## What it is
A multilingual research and learning repository analyzing the architecture of CLI coding agents, primarily Claude Code. It compiles deep-dive reports on telemetry, hidden features, tool systems, permissions, and agent harness mechanisms from public sources.

## Use cases
- understand how claude code agent architecture works
- learn how cli coding agents handle tools and permissions
- study agent loop and harness mechanisms
- research telemetry and privacy in ai coding tools
- learn about sub-agents and permission flows in coding agents

## When to choose
- you want to study how production coding agents like Claude Code are architected
- you need educational material on agent tool systems and permission models
- you prefer curated analysis reports in multiple languages

## When to avoid
- you need a runnable agent framework or library to build with
- you want production software rather than study notes
- commercial use is intended, as the repository prohibits it

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, developer-tools, documentation
- domain: large-language-models, developer-tools, tutorials
- platform: cross-platform
- tags: claude-code, cli-agent, architecture-analysis, reverse-engineering-notes, educational, ai-agents

## Member repositories
- sanbuphy/learn-coding-agent (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:52.134418+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:14.321785+00:00, confidence not recorded.
  - readme: https://github.com/sanbuphy/learn-coding-agent (fetched 2026-08-28T04:10:52.134418+00:00, sha 6759d20f212e)
- Data as of 2026-08-30T08:39:29.467469+00:00.