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 agentmods add commands/mturac/everything-openai-codex/evalgit clone --depth 1 https://github.com/mturac/everything-openai-codexWrote 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/commands/mturac/everything-openai-codex/eval)<a href="https://agentmods.dev/commands/mturac/everything-openai-codex/eval"><img src="https://agentmods.dev/badge/commands/mturac/everything-openai-codex/eval.svg" alt="Measured on agentmods" 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 | $0.00005 | $0.00452 |
| Opus 5 | $0.00003 | $0.00226 |
| Sonnet 5 | $0.00001 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
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 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.
This is a copy
95% identical to eval — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Eval Command
Evaluate implementation against acceptance criteria: $ARGUMENTS
Your Task
Run structured evaluation to verify the implementation meets requirements.
Evaluation Framework
Grader Types
-
Binary Grader - Pass/Fail
- Does it work? Yes/No
- Good for: feature completion, bug fixes
-
Scalar Grader - Score 0-100
- How well does it work?
- Good for: performance, quality metrics
-
Rubric Grader - Category scores
- Multiple dimensions evaluated
- Good for: comprehensive review
Evaluation Process
Step 1: Define Criteria
Acceptance Criteria:
1. [Criterion 1] - [weight]
2. [Criterion 2] - [weight]
3. [Criterion 3] - [weight]
Step 2: Run Tests
For each criterion:
- Execute relevant test
- Collect evidence
- Score result
Step 3: Calculate Score
Final Score = Σ (criterion_score × weight) / total_weight
Step 4: Report
Evaluation Report
Overall: [PASS/FAIL] (Score: X/100)
Criterion Breakdown
| Criterion | Score | Weight | Weighted |
|---|---|---|---|
| [Criterion 1] | X/10 | 30% | X |
| [Criterion 2] | X/10 | 40% | X |
| [Criterion 3] | X/10 | 30% | X |
Evidence
Criterion 1: [Name]
- Test: [what was tested]
- Result: [outcome]
- Evidence: [screenshot, log, output]
Recommendations
[If not passing, what needs to change]
Pass@K Metrics
For non-deterministic evaluations:
- Run K times
- Calculate pass rate
- Report: "Pass@K = X/K"
TIP: Use eval for acceptance testing before marking features complete.
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 First seen · 89 lines · 5 tokens per session scan A 5408482f5f5c
eval is a command published in the GitHub repository mturac/everything-openai-codex (89 stars, last pushed 11d ago), licensed MIT. It adds 5 tokens to every session and 452 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to eval, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
research
Research a technical or product question.
selfloop
Start or control a persistent SIPS loop whose only objective is improving SIPS and the agent operating it through measured, verified iterations.
dev-planner
Generate or update DEV-PLAN.md with phased development plan from Product-Spec.md.
patterns
Show the full agentpatterns report — success rate, approach→outcome correlation, top patterns.
verify
Spawn a fresh-context verifier subagent to check completed work against its specification before trusting it.