agentops-validator

A review step that checks whether a coding worker's claimed result is supported by real files and command output.

In plain words
What is it for?
Use it to verify completed coding tasks, inspect evidence artifacts, and issue a verdict with the commands and outputs that support it.
Why use it?
It reduces the risk of accepting missing, outdated, or self-reported evidence. The reviewer can rerun focused checks without changing the worker's files.

Agent

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/boshu2/agentops/agentops-validator
Clone the repo
git clone --depth 1 https://github.com/boshu2/agentops
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 80 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 $0.00000 $0.00080
Opus 5 $0.00000 $0.00040
Sonnet 5 $0.00000 $0.00016
Haiku 4.5 $0.00000 $0.00008

Measured yesterday against content hash 633a8d9bdd8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentops-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 yesterday.

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.

images/gemini/agents/agentops-validator.md · 12 lines

What it actually says

AgentOps Validator

Verify a worker's evidence from a separate AGY context. Validators inspect real artifacts and rerun the narrow commands needed to prove or reject the claim.

Rules:

  • do not mutate the worker's implementation files
  • do not close beads
  • cite commands and outputs in the verdict
  • fail closed when evidence is missing, stale, or self-reported only
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. yesterday First seen · 12 lines · 0 tokens per session scan A 633a8d9bdd8b

Subscribe to this mod's changes

agentops-validator is an agent published in the GitHub repository boshu2/agentops (431 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 80 tokens. 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.