代码深渊

简介

<p align="center"> <a href="https://telagod.github.io/code-abyss/"> <img src="https://raw.githubusercontent.com/telagod/code-abyss/main/assets/banner.svg" alt="Code Abyss — Personality, depth, and a security spine" width="100%"> </a> </p>

Composable persona · style · 30 engineering skills · 4 native security domains · self-evolution forge · code graph intelligence
for Claude Code · Codex CLI · Gemini CLI · OpenClaw

<p align="center"> <a href="https://www.npmjs.com/package/code-abyss"><img src="https://img.shields.io/npm/v/code-abyss?color=9b8cff&label=npm&style=flat-square" alt="npm"></a> <a href="https://github.com/telagod/code-abyss/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/telagod/code-abyss/ci.yml?branch=main&label=CI&style=flat-square" alt="CI"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-c4b8ff?style=flat-square" alt="MIT"></a> <a href="https://telagod.github.io/code-abyss/"><img src="https://img.shields.io/badge/site-pages-9b8cff?style=flat-square" alt="Site"></a> </p>

<p align="center"> <a href="https://telagod.github.io/code-abyss/"><b>Website</b></a> · <a href="docs/specs/tech-persona-card-v1.0.md"><b>Spec</b></a> · <a href="docs/README.zh-CN.md"><b>中文文档</b></a> · <a href="CHANGELOG.md"><b>Changelog</b></a> · <a href="https://telagod.github.io/code-abyss/submit.html"><b>Submit Persona</b></a> </p>

---

What's new in v4

• 4 native security domains — 4073 lines of original defense engineering (no Apache-2.0 upstream)
• 30 skills total, all SKILL.md ≤ 110 lines (avg 59), heavy content lives in references/
• 5 verify skills rewritten as judgment-type knowledge (when to use, how to interpret output, exemption rules)
• Office skills slim to under 100 lines each; 4 design systems consolidated into one selector skill
• v4.1 — self-evolution forge: cultivating-skills / cultivating-personas let the agent distill repeated workflows into reusable skills, with a safety scan and a three-tier publish funnel (local → project → community)
• v4.4 — hardware + academic writing: 3 new domain skills (KiCad EDA, hardware product pipeline, AIGC detection reduction) + prompt injection defense + execution-drive shared behavior
• v4.5 — dynamic persona loading: only abyss ships with npm — all other personas are fetched from GitHub on first use and cached locally, slimming the package
• v4.6 — code graph intelligence: abyss CLI builds a code relationship graph (call graph + temporal analysis) in seconds — caller tracing, impact analysis, hotspot detection, change coupling. Pre-edit hooks auto-check callers across all 4 platforms
• v4.7 — measured resolution: abyss v0.3.3 ships four-language reference resolution (Go / TypeScript / Python / Rust), benchmarked against SCIP ground truth across five corpora at ≥98.5% gated precision. Named-import binding tiers, receiver-type inference, and type-grade evidence — published numbers, not claims. npm install -g @code-abyss/cli

npx code-abyss -t claude -y --with-abyss

--with-abyss also downloads the abyss code-graph binary so the pre-edit hooks work out of the box; add --with-mcp to register abyss as an MCP server. Swap -t claude for codex / gemini / openclaw. Or as a Claude Code plugin:

claude plugin install code-abyss

Plain -y (no --with-abyss) installs only the persona/skills/style layer and skips the network — code-graph hooks stay dormant until abyss is on PATH. Interactive runs (drop the -y) prompt before downloading. Verify code-graph is live with abyss --version, then abyss index in any project.

---