Verdict
Evidence hold
Tracked record has insufficient claim-level editorial evidence for rollout use.
Decision depth: Preliminary monitored record. Not yet launch-audited for a rollout decision.
Evidence audit: automated extraction
Agent rollout decision record
Linear Agents
Evidence hold Pull-request and code-review agent: review official evidence before any pilot.
Permission footprint
Repository readnot evidenced
File editsnot evidenced
Shell commandsnot evidenced
Pull requestsnot evidenced
Issue/PR commentsnot evidenced
Network/API callsnot evidenced
Secrets/env varsnot evidenced
Sandboxingnot evidenced
Permission controlsnot evidenced
Audit loggingnot evidenced
Enterprise adminnot evidenced
Branch isolationnot evidenced
Human approvalnot evidenced
Production deploymentnot evidenced
Power level
Level 3: executes actions
Highest-risk evidenced power: pull-request creation
Controls separated
Required before pilot — organization must implement
least-privilege permissions, protected branches, mandatory human review, audit logs
Vendor-native control evidenced
branch isolation, security docs
Vendor-native control not evidenced
native sandbox, permission system, audit logs, admin console, SSO, data-retention settings
Pilot plan
Task class: Pull-request and code-review agent
Environment: non-production repository
Maximum access: pull-request creation
Reviewer: repo administrator and code owner
Success criteria: agent can comment or propose PR changes without bypassing branch policy
Stop conditions: organization-wide install or write permission is broader than approved
Prohibited: admin repo permissions, merge without human approval, organization-wide install without review
Blocking issues and unknowns
Blockers: Source health is docs risk.; Record has not been launch-audited for rollout use.; reads repository is not explicitly evidenced in the current source set.
Unknowns: Human editorial review pending.
Limitations: Tracked record depth is limited; do not use as an approval basis.
Claim-level evidence
reads repository
Linear Agents: reads repository
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for reads repository; treat as an evidence gap.
edits files
Linear Agents: edits files
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for edits files; treat as an evidence gap.
runs commands
Linear Agents: runs commands
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for runs commands; treat as an evidence gap.
opens pull requests
Linear Agents: opens pull requests
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for opens pull requests; treat as an evidence gap.
comments on issues or PRs
Linear Agents: comments on issues or PRs
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for comments on issues or PRs; treat as an evidence gap.
accesses secrets or environment variables
Linear Agents: accesses secrets or environment variables
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for accesses secrets or environment variables; treat as an evidence gap.
makes network/API calls
Linear Agents: makes network/API calls
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for makes network/API calls; treat as an evidence gap.
supports sandboxing
Linear Agents: supports sandboxing
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for supports sandboxing; treat as an evidence gap.
supports permission controls
Linear Agents: supports permission controls
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for supports permission controls; treat as an evidence gap.
provides audit logging
Linear Agents: provides audit logging
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for provides audit logging; treat as an evidence gap.
supports enterprise administration
Linear Agents: supports enterprise administration
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for supports enterprise administration; treat as an evidence gap.
supports branch isolation
Linear Agents: supports branch isolation
Status: not-evidenced · Reviewer: automated-extraction · Confidence: 24/100
Source: Linear official source set (official-docs)
Excerpt:
Limitations: No exact official-source excerpt was found for supports branch isolation; treat as an evidence gap.
Recent history
- boilerplate-change — rejected noise
Last successful source check: 2026-07-15T05:34:48.576Z
Alternatives
- No editorial alternatives set yet.
Receipt CTA
Generate a receipt that inherits this record depth, unsupported claims, inferred claims, source health, and expiry.
Check this agent for your environment