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 conorbronsdon/agent-skills --skill eval-integritygit clone --depth 1 https://github.com/conorbronsdon/agent-skillsWrote 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/conorbronsdon/agent-skills/eval-integrity)<a href="https://agentmods.dev/skills/conorbronsdon/agent-skills/eval-integrity"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-skills/eval-integrity.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 5.1 | $0.00107 | $0.02602 |
| Opus 5 | $0.00053 | $0.01301 |
| Sonnet 5 | $0.00021 | $0.00520 |
| Haiku 4.5 | $0.00011 | $0.00260 |
Grade A, and why
eval-integrity 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 7d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eval-integrity — Benchmark Credibility Audit
User-invokable auditor for LLM evaluation and benchmark repos. It answers one question: if you published this benchmark's numbers, would they survive an adversarial reviewer?
Most benchmark repos have a runner and a leaderboard but lack the integrity scaffolding that makes a published score mean what it appears to mean. This skill checks for that scaffolding, names what is missing, and rates whether each gap invalidates published numbers or is nice-to-have.
The checks below were extracted from hardening a real agent benchmark (cot-bench, a private podcast-evals repo) for an external grant review. Where a check needs a concrete example, cot-bench file names appear as illustrations — they are hints for what good looks like, not paths the auditor expects to find in your repo.
This is the static-analysis cousin of code-review: same parallel-subagent orchestration, but the subagents audit eval methodology instead of code correctness.
Invocation: deliberately model-invocable — read-only audit; it reports and offers fixes, never edits the benchmark.
When to Use
- Before submitting a benchmark to a grant, conference, or public leaderboard.
- When someone says "I don't trust those numbers" and you need to know if they're right.
- After building an eval, before publishing the first headline result.
- Periodically, as a benchmark accretes models and the leaderboard becomes load-bearing.
When NOT to Use
- A repo that is not an eval or benchmark (no scoring, no leaderboard, no judge). This skill has nothing to grade.
- A toy eval with no published numbers and no intent to publish. Integrity scaffolding is overhead until someone relies on the score.
Step 1: Confirm the target is a benchmark and locate its parts
Target: $ARGUMENTS (path to the benchmark repo; if empty, assume the current directory).
Establish the repo is gradable, then map where the audit will look. Run from the target repo root:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 165 lines · 107 tokens per session scan A 5ecc3bf22007
eval-integrity is a skill published in the GitHub repository conorbronsdon/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 2,602 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
mulmoterminal-model
Run MulmoTerminal sessions on something other than Anthropic's default, three ways — register an Anthropic-compatible backend (OpenRouter, Moonshot, a local Ollama bridge, a company gateway) as a providers entry in /.mulmoterminal/config.json, which has no Settings UI; pin a provider / model per project in its…
anthropic-api-knowledge-patch
Use this skill when building or migrating integrations for the Messages API, hosted platform variants, Managed Agents, structured outputs, tools, streaming, prompt caching, model selection, or rate-limit handling. Treat the project's actual SDK types, API responses, and model metadata as authoritative when they differ…
apache-flink-knowledge-patch
Use this skill when upgrading or operating Flink, writing DataStream or Table API jobs, changing SQL, implementing connectors, or diagnosing state, checkpoint, scheduling, and deployment behavior. Start with the quick checks, then open the topic reference that matches the work.
dagster-knowledge-patch
Use this skill when upgrading or maintaining Dagster definitions, Components, automation, execution infrastructure, storage, deployment configuration, or integration packages. Check the installed Dagster and integration-package versions first, then open the reference that matches the task.
dbt-knowledge-patch
Use this skill when maintaining dbt projects, packages, macros, automation, or adapter integrations that rely on current Core behavior. Start with the quick references below, then open the topic file that matches the task.
prompt-optimization
Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.