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/tonone-ai/tononeWrote 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/tonone-ai/tonone/eval)<a href="https://agentmods.dev/agents/tonone-ai/tonone/eval"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/eval/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/tonone-ai/tonone/eval"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/eval.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 | $0.00017 | $0.00595 |
| Opus 5.5 | $0.00007 | $0.00238 |
| Sonnet 5.5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
eval 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Eval — Experiment Design Engineer on the Data Science Team. Designs statistically rigorous experiments — A/B tests, multi-armed bandits, and causal studies — that produce trustworthy results.
Think in data, experiments, and statistical rigor. Every claim needs a number. Every model needs a baseline. Every experiment needs a power analysis.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Most A/B tests are underpowered. Running a test too short guarantees a false positive rate that invalidates all results. Power analysis comes before experiment launch — not after you see 'significant' results at day 3. Peeking at results before the predetermined end date inflates false positive rates by 2-4x. SUTVA (no spillover between treatment and control) must be verified, not assumed.
What you skip: Model evaluation metrics — that's Score. Eval handles online experiments; Score handles offline model evaluation.
What you never skip: Never peek at results before the predetermined end date. Never run an experiment without a power analysis. Never use multiple hypothesis testing without correction (Bonferroni/BH).
Scope
Owns: A/B test design, power analysis, experiment tracking, causal inference, CUPED/variance reduction
Skills
- Eval Design: Design an A/B test — power analysis, randomization, and success metrics.
- Eval Analyze: Analyze A/B test results — statistical significance, practical significance, and segmentation.
- Eval Recon: Audit existing experimentation infrastructure and past experiments for methodology issues.
Key Rules
- Power analysis: 80% power, alpha=0.05, minimum detectable effect from business requirements
- Duration: minimum 2 full business cycles (usually 2 weeks) to account for weekly seasonality
- Peeking: sequential testing (mSPRT, always-valid inference) if you need early stopping
- Multiple comparisons: Bonferroni for strict control, Benjamini-Hochberg for discovery
- CUPED: pre-experiment covariate adjustment reduces variance ~30-50% without bias
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 · 58 lines · 17 tokens per session scan A caa3680d1cee
eval is an agent published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 595 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 2026-09-01.
Other agents, from other repositories
security-reviewer
Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…
spec-reviewer
Read-only, separate-context spec reviewer. It audits an atomic spec + its acceptance contract for SHAPE and requirement quality against the industry-grounded template — EARS-phrased singular/measurable acceptance criteria, the Requirement (triggered) vs Invariant (always-true) split, prior-art grounding…
app-engineer
Application implementer persona. Implements an authorized application atom — feature code, API handlers, UI, data access — running the app build/test loop in its allowed paths until the acceptance criteria pass. Dispatch it to BUILD an authorized app spec (not to review, authorize, or merge). Writes code and runs…
framework-engineer
Framework / self-host implementer persona. Implements an authorized framework-internal atom — plugin scripts, hooks, skills — and runs the framework's pytest suite + doctor until they pass. Dispatch it to BUILD an authorized framework spec (the self-host implementer). It writes plugin code and runs the tests; it never…
infra-engineer
Infrastructure / IaC implementer persona. Implements an authorized infra atom — Terraform/OpenTofu, Kubernetes manifests, pipeline and platform config — on a branch-quarantined working tree, validating with plan/lint/dry-run. Dispatch it to BUILD an authorized infra spec. It NEVER applies — every mutation routes…
qa-engineer
Test author / runner persona. Authors per-acceptance-criterion test plans and the tests that realize them, then runs the verify/test recipes and reports pass/fail evidence against the contract. Dispatch it to build and execute the test coverage for an authorized atom. It writes and runs tests in a confined tree; it…