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/finalizenpx skills add skillberry-ai/cap-evolve --skill finalizegit 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 | $0.00069 | $0.01411 |
| Opus 5 | $0.00034 | $0.00705 |
| Sonnet 5 | $0.00014 | $0.00282 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
finalize 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
finalize — the one honest number
Optimization hill-climbs on val: every accept decision consumed val as a tuning
signal, so by the end of search val is optimistic — it has been selected
against. The number you report must come from data nothing was tuned against.
finalize scores the run's best candidate on the sealed test split, once, and
writes final.json. That file is the run's result.
One finalize is two evals, not one
A bare test number cannot be defended — a reader cannot tell whether it beat the
capability you started with. So one finalize scores test twice: the best
candidate as tag FINAL, and the untouched seed candidate as FINAL_seed
(harness.finalize). final.json therefore carries test, test_baseline,
baseline_id, and test_delta — the held-out improvement, which is the figure
report, the dashboard, and the event stream all headline. If the best candidate
IS the seed (nothing was accepted), the second eval is skipped and test_delta is
0 by construction.
So budget --n-trials 3 as 3 trials × 2 candidates × |test| rollouts — twice
what the flag looks like it buys on a paid benchmark.
Both evals sit inside one attempt and neither is a selection event: the delta is reported, never chosen on. That is why the seal counts attempts, not evals.
The seal (why "exactly once")
The instant test informs any choice — picking between finalists, "double-
checking" a low number, re-running until it looks better — it stops being held
out, because each peek is a selection event that pulls the number from an
unbiased estimate toward an optimistic fit metric (references/concepts.md).
cap_evolve enforces this in three parts (rundir.py:358-407), and the split
between them is the whole design:
- reserve — every
split="test"eval first checks the seal without burning it, so no phase other than finalize can reach test at all. - commit — the seal burns only after
final.jsonis written, so a finalize that dies before scoring leaves it unused and is honestly retryable. A transient crash must not destroy a run's headline number. - attempt guard — seal-on-success alone cannot tell "crashed before scoring"
from "crashed after". A real run hit the second case: a finalize killed by a
timeout had already scored test, the retry scored it again, and the reported
headline was that second look.
begin_test_attemptrefuses a retry once test rollouts exist on disk, before anything is spent.
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 · 105 lines · 69 tokens per session scan A ec7a5600c2f4
finalize is a skill published in the GitHub repository skillberry-ai/cap-evolve (47 stars, last pushed 2d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,411 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.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
evolve
Start or monitor an evolutionary development loop.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.