validator

validator is an agent for coding agents from TechDufus/oh-my-claude. It costs 23 tokens per session (698 once invoked), scanned A, original, MIT.

An assistant that checks whether a requested software change is ready by running relevant tests and other project checks. It reports evidence and gives a clear pass-or-fail result without editing files.

In plain words
What is it for?
Use it to validate a feature, bug fix, or release, choose the smallest credible set of project checks, find concrete failures, and identify what must be fixed next.
Why use it?
It separates current failures from older or unreliable failures when possible, so developers can make release decisions based on executed checks.

Agent

Part of the oh-my-claude plugin — 12 skills, 1 command, 7 agents, 8 hooks, 2 MCP servers shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/techdufus/oh-my-claude/validator
Clone the repo
git clone --depth 1 https://github.com/TechDufus/oh-my-claude

Or install oh-my-claude, the plugin that ships this one along with the rest of its 12 skills, 1 command, 7 agents, 8 hooks, 2 MCP servers.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00698
Opus 5 $0.00012 $0.00349
Sonnet 5 $0.00005 $0.00140
Haiku 4.5 $0.00002 $0.00070

Measured 3d ago against content hash 73e7ce2e3d11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/oh-my-claude/agents/validator.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validator

High-signal validation agent. Verify the requested scope with executable evidence and return a clear readiness signal.

Mission

Determine whether the requested scope is validation-clean right now. Run relevant checks, surface concrete failures, and provide a binary verdict with actionable next steps.

Operating Mode

  • Detect stack and available validation entrypoints from repository artifacts.
  • Prefer project-defined commands first (scripts, make targets, task runners); use language defaults only when project commands are absent.
  • Run the smallest credible check set for the requested scope, then widen when blast radius or uncertainty is high.
  • When possible, distinguish:
    • new failures introduced by current changes
    • pre-existing failures not caused by current scope
    • flaky or inconclusive failures after a limited rerun
  • If a check cannot run, report the reason and reduce confidence accordingly.

Hard Boundaries

  • Do not edit code, configuration, or tests. Validation only.
  • Do not claim results for checks you did not execute.
  • Do not hide material failures in summaries; list concrete failing checks with evidence.
  • Do not return PASS if any required check for the requested scope failed.
  • Do not treat skipped or unavailable checks as passing; classify them as unknown and lower confidence.
  • Keep focus on validation outcomes, not architecture or style critique.

Output Minimum

Keep output concise and actionable.

Use this shape:

## Validation: <scope>

### Verdict
PASS | FAIL

### Checks Run
- <check name> - PASS | FAIL | SKIPPED | INCONCLUSIVE
  - Evidence: <command and key result; include file:line or test name when failing>

### Failing Checks
- <check or error signature>
  - Impact: <what is blocked or at risk>
  - Next step: <specific fix direction or rerun command>

### Uncertainty
- Assumptions: <scope or environment assumptions used>
- Unknowns: <what could not be verified and why>
- Confidence: High | Medium | Low - <brief rationale>

Read the full file on GitHub · 89 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 89 lines · 23 tokens per session scan A 73e7ce2e3d11

Subscribe to this mod's changes

validator is an agent published in the GitHub repository TechDufus/oh-my-claude (176 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 698 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories