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.
git clone --depth 1 https://github.com/orin-dx/agent-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/orin-dx/agent-plugins/evaluation-runner)<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/evaluation-runner"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/evaluation-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/evaluation-runner"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/evaluation-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00620 |
| Opus 5 | $0.00015 | $0.00310 |
| Sonnet 5 | $0.00006 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
evaluation-runner 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 today.
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.
What it actually says
<load_first>
Load shared/references/evaluation/behavioral.md. Load only the selected fixture's public input before the target workflow finishes; reserve its oracle for the adjudicator.
</load_first>
WHEN preparing the run, THE SYSTEM SHALL expose only the fixture's public input to the target workflow.
WHEN a requested host capability is unavailable, THE SYSTEM SHALL record the limitation instead of substituting a different mode silently.
WHEN a started command or delegated task has not reached a terminal result, THE SYSTEM SHALL wait or terminate it and record the failure; a returned evaluation-run@1 SHALL have no pending checks.
THE SYSTEM SHALL NEVER edit the target artifacts after the workflow produces them.
THE SYSTEM SHALL NEVER read or disclose the fixture oracle before the target workflow reaches a terminal result.
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.
- today Changed · +1 lines a01638fdc9a6
- yesterday First seen · 43 lines · 31 tokens per session scan A 6bfd07d8c18e
evaluation-runner is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 620 once invoked, about $0.0002 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 2026-09-10.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
ring:test-reviewer
Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.
e2e-runner
End-to-end testing agent — writes and runs E2E tests to validate critical user processes.
flake-hunter
Hunts and stabilizes flaky tests — the ones that pass locally but fail on CI, fail every 50th run, or fail only on Mondays. Identifies the root cause (timing, shared state, async ordering, fixture pollution, network, randomness) and proposes a deterministic fix. Never just adds retries to hide flakes. Use when CI is…
tea
Master Test Architect and Quality Advisor.
os-architect-tester
Validation agent for os-architect. Runs pre-scripted user scenarios through the os-architect interview flow via Copilot CLI, evaluates whether classification, routing, and HANDOFFBLOCK output meet acceptance criteria, and produces a structured test report. Use to battle-harden os-architect after changes, or to…