Hi — I’ve been working on a verification layer for agent execution and evolution, and MetaClaw’s skills_only mode is a perfect fit for this.
This proposal adds deterministic verification to skill promotion without requiring RL or GPU compute.
Proposal: verified_skills mode — GPU-free skill evolution with deterministic improvement verification
Summary
MetaClaw's skills_only mode is excellent for operators without GPU access. However, skill promotion currently relies on LLM judgment — which is subjective and unauditable. This proposal adds a verified_skills mode that gates skill promotion on deterministic, cryptographically signed verification, eliminating the need for cloud RL while producing a trustworthy, auditable skill evolution history.
The Gap
In skills_only mode, the evolution loop works like this:
Conversation ends
↓
LLM analyzes session
↓
New skills extracted and summarized
↓
Skills promoted to permanent library
The problem: there is no deterministic check that a promoted skill actually improved performance. Promotion is gated on LLM self-evaluation, which is:
- Subjective (same inputs can produce different verdicts)
- Unverifiable by third parties
- Not auditable across environments
- Vulnerable to regression (a skill that hurts performance can be promoted)
In RL mode, weight updates provide a learning signal — but require cloud compute. In skills_only mode, there is no equivalent verification mechanism at all.
The Proposal: verified_skills mode
Add a new operating mode that sits between skills_only and rl:
Mode | GPU | Cloud | Verified | Auditable
--------------|-----|-------|----------|----------
skills_only | No | No | No | No
verified_skills (new) | No | No | Yes | Yes
rl | No | Yes | Partial | No
madmax | No | Yes | Partial | No
verified_skills adds one step to the existing skills_only loop:
Conversation ends
↓
LLM analyzes session (existing)
↓
New skills extracted (existing)
↓
NEW: Spec defined — "what does improvement look like?"
↓
NEW: SettlementWitness verifies deterministically
PASS → skill promoted with receipt_id attached
FAIL → skill rejected, counter-evidence logged
INDETERMINATE → flagged for human review
↓
NEW: receipt_id stored in skill metadata
↓
Full audit trail — every promoted skill is provably verified
SettlementWitness is a stateless verification oracle for agent workflows. It evaluates whether an output matches a specification and returns a cryptographically signed receipt (SAR — Settlement Attestation Receipt).
Key properties relevant to MetaClaw:
- Deterministic — identical inputs always produce identical verdicts
- Ed25519 signed — receipts are cryptographically verifiable
- Offline verifiable — no callbacks required after receipt is issued
- Stateless — no session state, no dependencies
- Free during adoption — no cost for integration
The verification call is simple:
import httpx
response = httpx.post(
"https://defaultverifier.com/settlement-witness",
json={
"task_id": f"skill-evolution-{skill_name}-{timestamp}",
"agent_id": f"{wallet}:metaclaw",
"spec": {
"improvement_type": "skill_promotion",
"skill_name": skill_name,
"expected": "skill improves agent performance on defined criteria"
},
"output": {
"skill_name": skill_name,
"skill_content": skill_content,
"evaluation_criteria": criteria,
"evaluation_result": evaluation_result
}
}
)
receipt = response.json()
verdict = receipt["receipt_v0_1"]["verdict"] # PASS | FAIL | INDETERMINATE
receipt_id = receipt["receipt_v0_1"]["receipt_id"]
Skill Metadata with Receipt
When a skill is promoted under verified_skills mode, its metadata includes the verification receipt:
{
"skill_name": "handle_api_rate_limits",
"version": "1.0",
"promoted_at": "2026-04-01T08:00:00Z",
"verified": true,
"receipt_id": "sha256:14be931e638ef93d043edc0c3feaf37bcbab33691b25997fefcef1b9b9062d00",
"verifier_kid": "sar-prod-ed25519-02",
"verdict": "PASS",
"promotion_source": "verified_skills"
}Unverified skills (promoted in skills_only mode) remain valid — this is fully backward compatible.
Rollback Logic
verified_skills mode enables something skills_only cannot: safe rollback.
# If a previously promoted skill later receives FAIL verdicts
# across N sessions, trigger rollback:
if fail_count >= ROLLBACK_THRESHOLD:
skill.status = "reverted"
skill.revert_reason = f"Failed verification {fail_count} times"
skill.reverted_at = timestamp
# Log counter-evidence receiptThis turns MetaClaw's skill library from append-only to self-correcting.
Why This Matters for Academic Rigor
MetaClaw's technical report describes skill evolution as a core contribution. The current implementation has a reproducibility gap: skill promotion decisions are made by an LLM judge whose outputs are non-deterministic across environments.
verified_skills mode closes this gap:
- Every promotion decision is deterministically reproducible
- Every receipt can be independently verified by any third party
- Skill evolution history becomes a cryptographically auditable record
- Results are comparable across environments and deployments
This directly strengthens the empirical claims in the technical report.
Implementation Scope
The change is contained and non-breaking:
New config option:
mode: verified_skills # new option alongside skills_only, rl, madmax
verification:
endpoint: "https://defaultverifier.com/settlement-witness"
agent_id: "your_wallet:metaclaw"
rollback_threshold: 3 # fail count before rollback triggers
require_pass_for_promotion: true
New dependency:
httpx # already likely present for proxy
No GPU. No cloud training backend. No Tinker API key required.
Files affected:
metaclaw/config.py — add verified_skills mode + verification configmetaclaw/skills/ — add receipt metadata to skill storage formatmetaclaw/trainer.py or equivalent — add verification gate before promotionREADME.md — document new mode in the mode comparison table
Integration Reference
A working reference implementation is available:
- Live endpoint:
https://defaultverifier.com/settlement-witness
- Public key registry:
https://defaultverifier.com/.well-known/sar-keys.json
- TypeScript SDK:
npm install sar-sdk ([sarprotocol.org](https://sarprotocol.org))
- Spec:
https://defaultverifier.com/spec/sar-v0.1
- MCP server:
https://defaultverifier.com/mcp
The endpoint is live, deterministic, and free to call. No API key required.
What This Enables for MetaClaw Users
For operators without GPU access:
- Full skill evolution capability without cloud compute costs
- Verified improvement history they can trust and audit
For researchers:
- Reproducible skill promotion decisions
- Cryptographic audit trail for empirical claims
- Cross-environment comparability
For the ecosystem:
- Promoted skills carry receipt_id — any downstream system can verify
- Skill libraries become portable, trustworthy artifacts
- Third parties can audit MetaClaw evolution history independently
Relationship to RL Mode
verified_skills is not a replacement for RL — it's a complement:
verified_skills → behavioral improvement via verified skill injection
no weight updates, no cloud, full verification
rl / madmax → weight updates via cloud training
+ optional SAR verification of weight update outcomes
A future verified_rl mode could add SAR verification gates to weight updates as well — only applying updates that produce PASS outcomes across a validation set.
Offer
Happy to:
- Contribute a reference implementation PR
- Provide test fixtures and sample receipts for validation
- Coordinate with the AIMING Lab team on spec alignment
This feels like a natural extension of MetaClaw’s architecture — bringing reproducibility and auditability to skill evolution.
The verification infrastructure is live and production-ready. Integration is a contained addition to the existing skill promotion flow.
Related:
Hi — I’ve been working on a verification layer for agent execution and evolution, and MetaClaw’s skills_only mode is a perfect fit for this.
This proposal adds deterministic verification to skill promotion without requiring RL or GPU compute.
Proposal:
verified_skillsmode — GPU-free skill evolution with deterministic improvement verificationSummary
MetaClaw's
skills_onlymode is excellent for operators without GPU access. However, skill promotion currently relies on LLM judgment — which is subjective and unauditable. This proposal adds averified_skillsmode that gates skill promotion on deterministic, cryptographically signed verification, eliminating the need for cloud RL while producing a trustworthy, auditable skill evolution history.The Gap
In
skills_onlymode, the evolution loop works like this:The problem: there is no deterministic check that a promoted skill actually improved performance. Promotion is gated on LLM self-evaluation, which is:
In RL mode, weight updates provide a learning signal — but require cloud compute. In
skills_onlymode, there is no equivalent verification mechanism at all.The Proposal:
verified_skillsmodeAdd a new operating mode that sits between
skills_onlyandrl:verified_skillsadds one step to the existingskills_onlyloop:What SettlementWitness Is
SettlementWitness is a stateless verification oracle for agent workflows. It evaluates whether an output matches a specification and returns a cryptographically signed receipt (SAR — Settlement Attestation Receipt).
Key properties relevant to MetaClaw:
The verification call is simple:
Skill Metadata with Receipt
When a skill is promoted under
verified_skillsmode, its metadata includes the verification receipt:{ "skill_name": "handle_api_rate_limits", "version": "1.0", "promoted_at": "2026-04-01T08:00:00Z", "verified": true, "receipt_id": "sha256:14be931e638ef93d043edc0c3feaf37bcbab33691b25997fefcef1b9b9062d00", "verifier_kid": "sar-prod-ed25519-02", "verdict": "PASS", "promotion_source": "verified_skills" }Unverified skills (promoted in
skills_onlymode) remain valid — this is fully backward compatible.Rollback Logic
verified_skillsmode enables somethingskills_onlycannot: safe rollback.This turns MetaClaw's skill library from append-only to self-correcting.
Why This Matters for Academic Rigor
MetaClaw's technical report describes skill evolution as a core contribution. The current implementation has a reproducibility gap: skill promotion decisions are made by an LLM judge whose outputs are non-deterministic across environments.
verified_skillsmode closes this gap:This directly strengthens the empirical claims in the technical report.
Implementation Scope
The change is contained and non-breaking:
New config option:
New dependency:
No GPU. No cloud training backend. No Tinker API key required.
Files affected:
metaclaw/config.py— addverified_skillsmode + verification configmetaclaw/skills/— add receipt metadata to skill storage formatmetaclaw/trainer.pyor equivalent — add verification gate before promotionREADME.md— document new mode in the mode comparison tableIntegration Reference
A working reference implementation is available:
https://defaultverifier.com/settlement-witnesshttps://defaultverifier.com/.well-known/sar-keys.jsonnpm install sar-sdk([sarprotocol.org](https://sarprotocol.org))https://defaultverifier.com/spec/sar-v0.1https://defaultverifier.com/mcpThe endpoint is live, deterministic, and free to call. No API key required.
What This Enables for MetaClaw Users
For operators without GPU access:
For researchers:
For the ecosystem:
Relationship to RL Mode
verified_skillsis not a replacement for RL — it's a complement:A future
verified_rlmode could add SAR verification gates to weight updates as well — only applying updates that produce PASS outcomes across a validation set.Offer
Happy to:
This feels like a natural extension of MetaClaw’s architecture — bringing reproducibility and auditability to skill evolution.
The verification infrastructure is live and production-ready. Integration is a contained addition to the existing skill promotion flow.
Related: