skill-eval

A testing aid for checking whether a coding-agent skill changes the agent’s behavior. It creates small scenarios with known flaws and measures whether the skill helps the agent notice and act on them.

In plain words
What is it for?
Use it to write and grade behavioral probes for skills, choose an appropriate testing tier, and report whether loading a skill affected the agent’s actions.
Why use it?
It prevents skill ratings from being based on tests that are too easy to reveal any difference. It also distinguishes an ineffective skill from a test where the agent already succeeds without it.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/boshu2/agentops/skill-eval
Any agent
npx skills add boshu2/agentops --skill skill-eval
Clone the repo
git clone --depth 1 https://github.com/boshu2/agentops

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,071 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.03071
Opus 5 $0.00030 $0.01536
Sonnet 5 $0.00012 $0.00614
Haiku 4.5 $0.00006 $0.00307

Measured 2d ago against content hash 2ca1e9d2a9d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-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 2d 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.

images/gemini/skills/skill-eval/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/skill-eval

Author one behavioral probe for one skill, at the cheapest tier that can still separate the arms, and report the verdict honestly. A probe measures behavior-change — did loading the skill change what the agent did — never quality-uplift. This skill authors and tiers probes. scripts/probe-skill.sh runs them.

Insight: when a probe returns INERT because the control arm already aces the scenario, the measurement failed, not the skill. Weakening the producer is one escape and it costs realism. The cheaper escape is to plant the defect: build a scenario containing exactly one flaw the discipline catches and a skim does not, then grade whether the agent acted on it. Signal you manufacture is signal you can reproduce.

The failure mode this exists to prevent: a skill catalog whose tier badges are editorial. A skill nobody measured is a skill nobody can defend, and re-running a saturated scenario at a lower effort level produces more rows in the ledger without producing more knowledge.

Modes

Trigger phrases Mode Entry point
"measure this skill", "does this skill do anything" author tier 1 (quiz probe) evals/skill-probes/<id>/
"the control arm aces it", "harden this scenario" author tier 2 (seeded-defect probe) references/seeding.md
"the probe came back INERT" diagnose headroom gate skill.probe-headroom
"run the probes" run a tier scripts/probe-skill.sh

Inputs

Required: the skill slug, and one sentence naming the action the skill should cause — a tool call made, an artifact written, a question raised, a sequence followed. If the sentence names a belief instead of an action ("understands that…", "considers…"), stop: that is not probeable, and rewriting it as an action is the actual work.

Optional: an existing probe id to harden.

Non-goals. This skill does not score output quality, rank skills, claim a skill is good, or gate a release. It does not run claude -p. It does not generalize from N=2 — small N is directional and every artifact it produces says so.

Read the full file on GitHub · 234 lines

Changes

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.

  1. 2d ago First seen · 234 lines · 61 tokens per session scan A 2ca1e9d2a9d0

Subscribe to this mod's changes

skill-eval is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 4d ago), licensed Apache-2.0. It adds 61 tokens to every session and 3,071 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

brainstorm

Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or…

OutlineDriven/odin-claude-plugin · 85 tokens

autolearn

Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.

OutlineDriven/odin-claude-plugin · 65 tokens

doc-review

Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.

OutlineDriven/odin-claude-plugin · 32 tokens

audit-project

Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".

OutlineDriven/odin-claude-plugin · 50 tokens

commit-push-pr

Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

OutlineDriven/odin-claude-plugin · 31 tokens

doubt-driven

Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.

OutlineDriven/odin-claude-plugin · 49 tokens