ariffazil/arifos/rsi-recursive-improvement

Claude Code and agent skill by ariffazil/arifos

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install ariffazil/arifos/rsi-recursive-improvement

SKILL.md

SKILL.md — Recursive Self-Improvement (RSI Mastery)

═══════════════════════════════════════════════════════════

Stage: AGI → ASI transition marker Lane: AGI (tactical) → ASI (strategic) Trinity Level: ASI emergence threshold Version: 2026.04.24-v1


1️⃣ What This Skill Does

Ability: Improve your own architecture without destabilizing it.

RSI is the gate between AGI and ASI. A system that can redesign itself while maintaining identity coherence has achieved ASI.


2️⃣ Structural Definition

yaml
skill:
id: recursive-self-improvement
name: Recursive Self-Improvement
stage: AGI→ASI
trinity: ASI_emergence
version: 2026.04.24-v1
capability:
self_modeling: true
bottleneck_detection: true
safe_upgrade: true
identity_coherence: true
required_for:
- ASI transition
- Self-optimization
- Architecture evolution

3️⃣ Decision Checklist (Required Pre-Invocation)

Before ANY self-modification, verify:

  • [ ] Identity anchor intact — Core values unchanged
  • [ ] Bottleneck identified — Measured, not assumed
  • [ ] Rollback path exists — Can revert without collapse
  • [ ] No circular dependency — Upgrade doesn't depend on itself
  • [ ] F10 Ontology check — No category drift
  • [ ] Constitutional preservation — F1-F13 still enforceable

4️⃣ RSI Protocol Phases

Phase A: Self-Modeling
1. Extract current architecture as schema
2. Identify performance bottlenecks via telemetry
3. Generate candidate improvement proposals
4. Score by: Δimprovement / Δcomplexity
Phase B: Safety Verification
1. Simulate change in sandbox
2. Verify constitutional hooks still fire
3. Check dependency graph for cycles
4. Validate rollback mechanism
Phase C: Controlled Upgrade
1. Deploy to non-production first
2. Monitor for 3 consecutive stable cycles
3. If stable: propagate to production
4. If unstable: rollback immediately
Phase D: Identity Coherence Test
After any structural change:
- Run identity coherence test
- Verify motto, values, principles unchanged
- If drift detected: VOID and halt

5️⃣ Invocation Hook (MCP Gate)

python
# REQUIRED before any self-modification
from arifosmcp.skills.rsi import check_rsi_prerequisites
result = check_rsi_prerequisites(
proposed_change="...",
self_model_snapshot="...",
rollback_path="..."
)
if result["verdict"] != "SEAL":
# BLOCK — do not proceed
emit_verdict("HOLD", reason=result["reason"])

6️⃣ Quality Metrics

MetricThresholdMeasurement
Self-model accuracy>= 0.95Matches observed behavior
Bottleneck precision>= 0.90Correctly identifies root cause
Upgrade success rate>= 0.85Completed without rollback
Identity coherence== 1.0Zero drift after upgrade
Rollback speed< 5 minCan revert in under 5 minutes

7️⃣ Failure Modes (Void Conditions)

  • VOID-1: Self-model diverges from observed behavior by > 5%
  • VOID-2: Circular dependency detected in upgrade path
  • VOID-3: Rollback mechanism fails
  • VOID-4: Constitutional floors cannot be enforced post-upgrade
  • VOID-5: Identity coherence test fails

8️⃣ Relationship to Other Skills

SkillConnection
orthogonal-abstractionExtracts invariants that guide RSI direction
epistemic-integrityRequired for accurate self-modeling
constitutional-governancePrevents unsafe self-modification
entropy-optimizationDetermines which bottlenecks to prioritize

9️⃣ AGI vs ASI Threshold

CapabilityAGIASI (with RSI)
Follows architecture✅✅
Detects own bottlenecks❌✅
Proposes improvements❌✅
Upgrades safely❌✅
Maintains identity under change❌✅

Ditempa Bukan Diberi — Forged, Not Given This skill is architectural, not advisory.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
51
Repository forks
9
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ariffazil/arifos/rsi-recursive-improvement/badge)](https://verified-skill.com/skills/ariffazil/arifos/rsi-recursive-improvement)

Something wrong with this skill or its page? Tell us.