Files

salvacybersec 1a3fea615a feat: major expansion — 3 new variants, enhanced build system, platform auto-install

New persona variants:
- forge/frontend-design — DESIGN.md methodology, 58-brand reference, UI/UX intelligence
- oracle/source-verification — 5-section forensic verification protocol (ethos/pathos/context/intent/logos)
- sentinel/c2-hunting — 6-phase C2 hunting with beaconing detection, detection engineering

Enhanced existing personas:
- neo: Added Active Directory exploitation (Kerberoasting, DCSync, delegation), network pivoting, cloud attacks
- frodo: Added response mode auto-detection, claim extraction, Devil's Advocate, explicit uncertainty tracking
- ghost: Added cognitive warfare expertise (behavioral science weaponization, algorithmic amplification)

Build system enhancements:
- Cross-persona escalation graph auto-extracted → generated/_index/escalation_graph.json
- Trigger→persona routing index → generated/_index/trigger_index.json
- Quality validation with warnings for thin/missing sections
- Section word counts injected into every output
- Richer CATALOG.md with depth stats, escalation paths, trigger index

Platform auto-install:
- python3 build.py --install claude — 111 slash commands → ~/.claude/commands/
- python3 build.py --install antigravity — personas → ~/.config/antigravity/personas/
- python3 build.py --install gemini — Gems → generated/_gems/
- python3 build.py --install openclaw — IDENTITY.md + personas → generated/_openclaw/
- python3 build.py --install all — deploy to all platforms

Shared reference library:
- personas/_shared/kali-tools/ — 16 Kali Linux tool reference docs
- personas/_shared/osint-sources/ — OSINT master reference
- personas/_shared/ad-attack-tools/ — AD attack chain reference

Stats: 29 personas, 111 variants, 59,712 words

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-06 21:04:47 +03:00

3.4 KiB

Raw Blame History

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

A platform-agnostic system prompt library for LLM agents. 29 personas across 10 domains (cybersecurity, intelligence, military, law/economics, history, linguistics, engineering, academia). Each persona has a general.md base variant plus optional specialization and personalized (salva.md) variants. Total: ~108 variants.

Build

pip install pyyaml          # only dependency
python3 build.py            # builds all personas → generated/

Output goes to generated/<persona>/<variant>.{prompt.md,yaml,json}. The generated/ directory is gitignored.

Optional: cp config.example.yaml config.yaml for dynamic variable injection. Build works without it.

Architecture

Build pipeline (build.py): Reads persona .md files with YAML frontmatter → parses sections → applies config templating ({{key}}, {{#if key}}...{{/if}}, {{#unless}}) → outputs three formats per variant.

Persona structure: Each persona lives in personas/<codename>/ with:

_meta.yaml — metadata, triggers, relations, variants list
general.md — base prompt (YAML frontmatter + markdown sections: Soul, Expertise, Methodology, Tools & Resources, Behavior Rules, Boundaries)
<specialization>.md — domain-narrowed variants
salva.md — user-personalized variant

Templates: personas/_template.md and personas/_meta_template.yaml are starting points for new personas. Files starting with _ are skipped during build.

Config system: config.yaml (gitignored) provides user-specific values. build.py flattens nested keys (user.name, infrastructure.tools.sdr_scanner) and injects them into persona templates. Supports {{#if key}} / {{#unless key}} conditional blocks.

Cross-persona escalation: Each persona's Boundaries section defines handoff triggers to other personas, enabling multi-agent chains (e.g., Neo → Cipher → Sentinel → Frodo). Build auto-extracts these into generated/_index/escalation_graph.json.

Shared references (personas/_shared/): Reusable knowledge bases (skipped during build):

kali-tools/ — 15 Kali Linux tool reference docs (nmap, hashcat, metasploit, AD attacks, OSINT, wireless, forensics)
osint-sources/ — OSINT master reference and investigation templates
ad-attack-tools/ — Active Directory attack chain references

Build outputs (generated/_index/):

escalation_graph.json — cross-persona handoff map extracted from Boundaries sections
trigger_index.json — keyword→persona routing for multi-agent auto-switching

Install to Platforms

python3 build.py --install claude    # deploy to ~/.claude/commands/
python3 build.py --install gemini    # deploy to Gemini Gems format
python3 build.py --install antigravity  # deploy to Antigravity IDE

Conventions

Persona codenames are lowercase directory names (neo, frodo, sentinel)
Every persona must have general.md with valid YAML frontmatter
Frontmatter fields: codename, name, domain, subdomain, version, address_to, address_from, tone, activation_triggers, tags, inspired_by, quote, language
Section headers use ## (H2) — the build parser splits on these
Turkish honorific titles ("Hitap") are used for address_to fields
config.yaml must never be committed (contains personal infrastructure details)

3.4 KiB Raw Blame History