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 skills/skillberry-ai/cap-evolve/evaluatenpx skills add skillberry-ai/cap-evolve --skill evaluategit clone --depth 1 https://github.com/skillberry-ai/cap-evolveWhat 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 | $0.00084 | $0.02254 |
| Opus 5 | $0.00042 | $0.01127 |
| Sonnet 5 | $0.00017 | $0.00451 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
evaluate 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evaluate — honest, multi-trial scoring
Turns a candidate into a score you can trust. A reward number is only as honest
as the variance around it and as the denominator under it: agents are stochastic,
and infrastructure fails. evaluate produces a point estimate, its uncertainty, and
the count of tasks that actually produced a measurement. The math lives in
cap_evolve.stats; this skill drives the adapter and aggregates.
What it produces
A SplitResult (core/cap_evolve/loop.py:59-115):
reward— the mean, over the tasks that were scored, of each task's mean over its valid trials (harness.py:405-414,loop.py:127-131). Not the mean over every task in the split — see the next section.n_tasks/n_scored(andcoverage = n_scored/n_tasks,loop.py:79-84) — the honest denominator. Read these on every result, neverrewardalone.stderr— the combined SE of that reported mean: between-task variance (do different tasks agree?) folded with within-task trial variance (is the agent consistent on a fixed task?),stats.combined_stderr. This is what the report prints and what the gate'ssignificantmode consumes — not what the default gate reads; see "What the gate actually consumes".pass_k— when trials > 1, the estimated probability that all k i.i.d. trials pass (reliability). Alsopass_at_k— at least one of k passes (capability). Opposite questions; seereferences/concepts.md.- per-task scores + feedback, and the rollout files
diagnosereads:<run-dir>/rollouts/<split>/<task>__<tag>__t<k>.json(harness.py:334).
A crashed rollout is missing data, not a zero
The single largest honesty mechanism in the eval path. Two ways a trial produces no measurement:
- the runner errored (
rollout.errorset) — the target never ran; - the rollout succeeded and the scorer could not grade it (crashed grading
harness, missing report file). There is no
rollout.error, so adapters must flag it by settingScore.raw["errored"](harness.py:308-323). An adapter that doesn't is how a scorer outage becomes a real 0.0.
What ships with it
6 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.
- 2d ago First seen · 137 lines · 84 tokens per session scan A 3366d08a36e8
evaluate is a skill published in the GitHub repository skillberry-ai/cap-evolve (47 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,254 once invoked, about $0.0004 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.
Other skills, from other repositories
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
prisma-upgrade-v7
Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…