AI Dispatch
agent · coding agent

Claw Code

Reviewed12 or more fields evidenced, and scored by a human against the published rubric

15 fields evidenced · 40 with no public information. Every value below links to the document it came from and the date we checked it.

14 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist

4 of those are flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated them yet.

Runtime governance
2/3

Are scope, spend, and authority enforced while the agent runs?

Claw Code publishes enforced run-time authority limits: "19 permission-gated tools - file I/O, shell execution, Git operations, web scraping, notebook editing - each independently sandboxed with configurable access controls", stated under "Core Capabilities" as the project's own architecture. Authority is gated per tool, but no spend cap or scope budget is published, so this is short of full scope/spend/authority enforcement.

Audit trail
0/3

Is there a tamper-evident record of what it actually did?

No public evidence found. The only append-only-log claim on the page ("It is backed by an independent append-only log system") appears under "Patterns Revealed by the Source Leak", describing KAIROS Mode in the leaked Claude Code implementation, which the page states was "entirely hidden from external builds in the original implementation" and which Claw Code does not replicate. That field was rejected this run as misattributed; no audit record of Claw Code's own actions is published.

How this gap gets closed →
Compliance
0/3

Are compliance obligations attached per engagement?

No public evidence found. The page checked publishes no certification, audit, attestation, or regulatory framework mapping.

How this gap gets closed →
Outcome settlement
0/3

Does payment depend on a verified result?

No public evidence found of payment linked to a verified outcome. The page states the project is "Free and open source", so no payment is taken and no settlement mechanism exists.

How this gap gets closed →
Insurance & indemnity
0/3

Can the deployment be insured, and is the customer indemnified?

No public evidence found. The page checked names no carrier, cover, limit, or customer indemnity.

How this gap gets closed →

Assurance

Insurance available
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Insurance carriers
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Coverage limits
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Indemnification
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Liability cap
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Audit trail
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Tamper-evident log
Vendor describes an independent append-only log system backing the agent; the same sentence states it was hidden from external builds in the original implementation, so customer reviewability is not established.
It is backed by an independent append-only log system, entirely hidden from external builds in the original implementation.
claw-code.codes · checked Aug 6, 2026
Explainability
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Runtime governance
Each capability — file reading, Bash execution, web scraping, LSP integration, Git operations — is implemented as a self-contained tool with granular permission controls .
claw-code.codes · checked Aug 6, 2026
Permission scopes
Each capability — file reading, Bash execution, web scraping, LSP integration, Git operations — is implemented as a self-contained tool with granular permission controls .
claw-code.codes · checked Aug 6, 2026
Compliance certifications
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Regulatory alignment
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Outcome-based pricing
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Settlement mechanism
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Dispute process
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
SLA terms
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Evaluation coverage
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Agency

Autonomy level
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Human oversight
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Goal complexity
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Action space
reads your entire codebase, edits files, executes commands, runs tests, handles Git
claw-code.codes · checked Aug 6, 2026
Operating environment
Terminal-native agent
claw-code.codes · checked Aug 6, 2026
Initiative
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Safety

Safety evaluations
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Red teaming
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Safety policy
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Usage restrictions
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Model or system card
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Incident reporting
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Third-party evaluations
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Data handling
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Practicality

Pricing model
Free and open source
claw-code.codes · checked Aug 6, 2026
Price point
Free and open source
claw-code.codes · checked Aug 6, 2026
Availability
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Deployment options
no public information

Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences

claw-code.codes · checked Aug 6, 2026
Integrations
MCP Integration Full Model Context Protocol (MCP) support with 6 transport types — Stdio, SSE, HTTP, WebSocket, SDK, and ClaudeAiProxy.
claw-code.codes · checked Aug 6, 2026
Supported regions
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Support model
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Foundation models

Base models
Provider-agnostic (Claude, OpenAI, local models)
claw-code.codes · checked Aug 6, 2026
Model provider
Provider-agnostic (Claude, OpenAI, local models)
claw-code.codes · checked Aug 6, 2026
Model swappable
Provider-agnostic (Claude, OpenAI, local models)
claw-code.codes · checked Aug 6, 2026
Open weights
No proprietary code. No model weights.
claw-code.codes · checked Aug 6, 2026
Fine-tuning
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Context window
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Ecosystem

Protocols supported
MCP Integration Full Model Context Protocol (MCP) support with 6 transport types — Stdio, SSE, HTTP, WebSocket, SDK, and ClaudeAiProxy.
claw-code.codes · checked Aug 6, 2026
Tool use
no public information

Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences

claw-code.codes · checked Aug 6, 2026
Multi-agent
The framework supports spawning sub-agents — internally referred to as "swarms" — to parallelize complex tasks.
claw-code.codes · checked Aug 6, 2026
API access
no public information

Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences

claw-code.codes · checked Aug 6, 2026
Open source
Open Source · Python + Rust
claw-code.codes · checked Aug 6, 2026
Marketplace presence
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Impact

User base
no public information

Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences

claw-code.codes · checked Aug 6, 2026
Deployment scale
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Target sectors
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
High-risk domains
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this
Documented incidents
no public information
claw-code.codes · checked Aug 6, 2026 · source did not state this

Compared with

Side-by-side on the fields where Claw Code and the other entry are both on record and actually differ.