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.
npx skills add cherninlab/ennodia --skill benchmark-criticgit clone --depth 1 https://github.com/cherninlab/ennodiaWrote 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/skills/cherninlab/ennodia/benchmark-critic)<a href="https://agentmods.dev/skills/cherninlab/ennodia/benchmark-critic"><img src="https://agentmods.dev/badge/skills/cherninlab/ennodia/benchmark-critic/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/skills/cherninlab/ennodia/benchmark-critic"><img src="https://agentmods.dev/badge/skills/cherninlab/ennodia/benchmark-critic.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 | $0.00025 | $0.00130 |
| Opus 5.5 | $0.00010 | $0.00052 |
| Sonnet 5.5 | $0.00005 | $0.00026 |
| Haiku 4.5 | $0.00003 | $0.00013 |
Grade A, and why
benchmark-critic 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 1mo 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.
What it actually says
Benchmark Critic
Review benchmark ideas or results for credibility.
Look for:
- a fair single-model baseline
- a fair Ennodia or multi-agent condition
- deterministic fixtures where possible
- clear scoring rules before results are collected
- leakage from oracle answers into prompts
- cherry-picked tasks or missing negative examples
- enough raw outputs to let others inspect the result
Recommend the smallest benchmark that can show useful signal without pretending to prove more than it does.
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.
- 1mo ago First seen · 21 lines · 25 tokens per session scan A d4b284769cd3
benchmark-critic is a skill published in the GitHub repository cherninlab/ennodia (6 stars, last pushed 29d ago), licensed MIT. It adds 25 tokens to every session and 130 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
simulation-validator
Validate simulations across three stages — run pre-flight checks on configuration files (parameter ranges, required fields, disk space), monitor runtime logs for residual growth, NaN/Inf, and adaptive dt collapse, and perform post-flight validation of results (physical bounds, mass/energy conservation, convergence).…
skill-evaluator
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta…
agent-evals
A method for testing AI agents by examining what they actually did during a run, including their tool use and execution steps. It also covers building test cases from real production runs and comparing automated judgments with human labels.
agent-puzzles
Competitive puzzle arena for AI agents with timed solving, per-model leaderboards, and 5 categories (reverse captcha, geolocation, logic, science, code). Use when solving puzzles, tracking rankings, creating new challenges, or benchmarking agent capabilities.
unlimited-mcp-selftest
Run the unlimited-mcp regression battery (Tier 0 lint+types, Tier A automated, Tier B live end-to-end) and report pass/fail per step. Use when the user says "run the regression suite", "run the battery", "selftest", "test everything", or before a version bump. Requires the unlimited-mcp server connected…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.