Reviso Evidence — Development agent for Claude Code
Reviso Stage 4 evidence agent — re-examines one candidate against the code and returns findings of fact.
How to install Reviso Evidence
Installs to ~/.claude/agents/vyttle-llc-reviso-reviso-evidence.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Vyttle-LLC/reviso/HEAD/agents/reviso-evidence.md -o ~/.claude/agents/vyttle-llc-reviso-reviso-evidence.md Restart Claude Code, or start a new session, for it to be picked up.
What Reviso Evidence does
name: reviso-evidence description: Reviso Stage 4 evidence agent — re-examines one candidate against the code and returns findings of fact. No score, no verdict, no veto. tools: Read, Grep, Glob, Bash(git blame:*), Bash(git log:*), Bash(git diff:*), Bash(git show:*) model: sonnet
You re-examine a single code-review candidate against the real code and return findings of fact. You do not judge the candidate — no score, no verdict, no veto; judgment belongs to the orchestrator, which holds
Alternatives in Development
- Review Fact Checker — Verify every factual claim in a review draft against vault sources 4.6k ★
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Finding Adjudicator — Independent finding adjudication as a distinct work type 17 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Self Review Verifier
Read-only adversarial verifier for the self-review loop. Takes one or more candidate findings plus the scope f
Claim Auditor
Adversarial verifier for proposed genealogical matches. Tries to break each proposed match with evidence, kill
Triage Critic
Independently grades a submittal/RFI triage brief PDF against the source package and returns a 1-10 score with
Stamity Reviewer
Reviews a change set across ten quality lenses and returns a verdict with confidence and graded findings, each
Adversarial Judge.Agent
Use to adversarially evaluate a proposal or implementation against its repository profile and specs, returning
Goal Verifier Agent
Goal-level checker for the /goal loop: evaluates a goal's completion_criteria against repo reality and returns
Related Skills
Helpful Content Review Skill
A Claude skill that reviews and scores any draft or live page against Google's helpful, reliable, people-first
Codebase Tribunal
⚖️ Your codebase is on trial: 5-8 AI expert personas (PM/architect/backend/security/QA/DevOps) audit any proje
Claim Audit
A Claude skill that audits AI-written text claim by claim: quotes each checkable claim, tags it with one of te