code-abyss

The problem

Most AI coding agents have no memory of who they are. They respond in the same flat tone whether they're debugging a race condition, reviewing architecture, or triaging a P0 incident. They forget your conventions between sessions. They flip-flop on advice. They sound like a help-desk script.

And when you ask them about security — pentest, code audit, threat modeling, IR — most agents fall back to generic OWASP recitation, because the underlying skill library was never written by people who actually run red/blue/purple teams.

You don't want a help desk. You want a principal engineer who shows up with a personality, executes consistently, closes the loop — and has a security spine when things get real.

What Code Abyss does

One command installs three composable layers into your agent's runtime:

┌─────────────────────────────────────────────────────┐
│  Identity     who it is     →  config/personas/*.md │
│  Behavior     how it acts   →  _shared/*.md         │
│  Style        how it sounds →  output-styles/*.md   │
└─────────────────────────────────────────────────────┘

  6 personas  ×  6 styles  =  36 validated combinations

Pick any persona. Pair it with any style. The behavior layer (iron laws, execution chains, proactive protocol, skill routing) stays constant. Your agent becomes a consistent character with structured execution and domain expertise across every session.

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.

Personas

CORE · LITERARY

邪修红尘仙 · abyss

吾 → 魔尊

Security-first dark cultivator. Direct, decisive, closes every loop. Ships with npm — works offline.

#security #xianxia #decisive

REMOTE · LITERARY

文言小生 · scholar

在下 → 前辈

Literary Chinese scholar. Treats code as poetry, debugging as puzzle-solving.

#literary #classical #meticulous

REMOTE · CASUAL

知性大姐姐 · elder-sister

姐姐 → 小宝

Warm mentor. Wraps sharp judgment in genuine care. Guides through questions.

#gentle #mentoring #insightful

REMOTE · PLAYFUL

古怪精灵小师妹 · junior-sister

本仙女 → 师兄

Hyperactive bug hunter. Roasts bad code, then silently fixes it.

#playful #energetic #chaotic

REMOTE · CASUAL

铁壁暖阳 · iron-dad

哥 → 宝子

Dependable big brother. Absorbs pressure, radiates warmth. Dad-joke equipped.

#warm #dependable #protective

REMOTE · COMMUNITY

东北魅影·雨姐 · dongbei-yujie

姐 → 老蒯

Sharp-tongued Northeast code overseer. Cuts straight to the bug, then patches the road. Creator: wons

#dongbei #blunt #principal

Core persona (abyss) ships with npm and works offline. Remote personas are fetched from GitHub on first --persona <slug> use and cached at ~/.code-abyss/personas/.

# Mix freely — any persona × any style
npx code-abyss -t claude --persona elder-sister --style abyss-cultivator -y
# → fetches elder-sister on first run, cached thereafter

Browse the full gallery →

Security suite (v4 highlight)

4 native security skills, 4073 lines of original engineering content. No Apache-2.0 upstream — every example, every detection signal, every defense pattern is written for this project.

Plus securing-systems as the router skill covering pentest, code audit, red/blue/purple team operations. Every attack technique ships with the matching detection signal and mitigation pattern — "with offense as defense" is structural, not lip service.

Code graph intelligence (powered by abyss)

Your agent can now see code relationships. The abyss CLI builds a full call graph, temporal analysis, and hotspot map — in seconds, with zero cloud dependencies.

The indexing-code skill automatically hooks into all 4 supported platforms — before every Edit/Write, the agent checks callers and warns about high-impact changes. Available as a CLI via the agent's shell tool, or as an abyss mcp server (7 tools over stdio).

Resolution is measured, not asserted. abyss resolves call references through tiered heuristics, each tagged with a confidence score, and benchmarks itself against SCIP (compiler-grade) ground truth across four languages and five corpora — published whatever the numbers say: