hill-climb

hill-climb is a skill for Claude Code from skillberry-ai/cap-evolve. It costs 120 tokens per session (2,318 once invoked), scanned A, original, Apache-2.0.

A hill-climbing method for improving an AI coding agent by repeatedly creating a modified candidate and keeping it when validation results show a meaningful improvement. Validation data is used during tuning, while test data is saved for the final check.

In plain words
What is it for?
Optimizing an agent against coding tasks, especially when results are pass-or-fail or the task set is small, after a baseline result has been created.
Why use it?
It provides a defined search process for deciding whether changes are better, without changing the current best version when an iteration fails.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Optimizing an agent against coding tasks, especially when results are pass-or-fail or the task set is small, after a baseline result has been created.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skillberry-ai/cap-evolve/hill-climb
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.

Any agent
npx skills add skillberry-ai/cap-evolve --skill hill-climb
Clone the repo
git clone --depth 1 https://github.com/skillberry-ai/cap-evolve

Made for: Claude Code.

Wrote 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.

agentmods badge for hill-climb

README.md
[![agentmods](https://agentmods.dev/badge/skills/skillberry-ai/cap-evolve/hill-climb.svg)](https://agentmods.dev/skills/skillberry-ai/cap-evolve/hill-climb)
Your own site
<a href="https://agentmods.dev/skills/skillberry-ai/cap-evolve/hill-climb"><img src="https://agentmods.dev/badge/skills/skillberry-ai/cap-evolve/hill-climb.svg" alt="Measured on agentmods" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,318 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00120 $0.02318
Opus 5 $0.00060 $0.01159
Sonnet 5 $0.00024 $0.00464
Haiku 4.5 $0.00012 $0.00232

Measured 8d ago against content hash e4738eab24c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hill-climb 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 8d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/_bootstrap.py, scripts/abstract.py, scripts/check.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/algorithms/hill-climb/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hill-climb — one loop, three focus schedules

Greedy search over candidates: the parent is always the run's current best, and a child replaces it only by clearing the val significance gate. The test split is never touched here — that is finalize.

Requires baseline first. Without --resume the loop reads the seed's val result from <run-dir>/baseline.json (scripts/run.py:121-122); with no run state it raises FileNotFoundError: no run state at .../state.json. --resume instead reads the current best's val from its stored rollouts, falling back to baseline.json when the run has no best yet (run.py:118-122).

One iteration, end to end

This is the mechanism the other algorithm skills vary; they describe only their differences and point back here. One iteration is harness.run_step (core/cap_evolve/harness.py:1409):

  1. Pick the parent — always the current best (harness.py:2224, run_dir.candidate_dir(run_dir.best_id)). Copy it to work/<cand_id>/; the optimizer edits that copy in place, so the parent is never mutated (harness.py:1454-1458).
  2. Build the prompt. The parent's val per-task rows are split into always-failing / flaky / infra-errored / solid (harness.py:1775-1795), rendered as the failure index plus an explicit protect these passing ids block (harness.py:1803-1879), and substituted into the project's optimizer-instructions template. --focus narrows which failures are emphasized; nothing else changes.
  3. Inject context and memory. Full trajectories, capability guidance, and the four cross-iteration files land in the workdir (harness.py:1062-1094) — see references/run-step.md.
  4. Optimize. The optimizer command mutates the workdir. A crash is caught, logged, and left as an unchanged copy of the parent, so the gate simply rejects it — a wasted iteration, not a dead run (harness.py:1486-1500).
  5. Evaluate on val only (harness.py:1516), at --n-trials trials per task.
  6. Gate. With per-task data on both sides the paired test is chosen automatically: accept iff mean per-task Δ > k·SE of those paired deltas (harness.py:1524-1532). --no-regression adds a second, harder condition on top.
  7. Commit. Every candidate is snapshotted — accepted and rejected — so any iteration can be diffed (harness.py:1557); the version store commits it (harness.py:1609-1612). Only an accepted candidate calls set_best and becomes the next parent (harness.py:1558-1559); a rejected one is filed in the rejected memory that feeds the next prompt (harness.py:1607-1608).

Read the full file on GitHub · 152 lines

Files

What ships with it

7 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.

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. 8d ago First seen · 152 lines · 120 tokens per session scan A e4738eab24c8

Subscribe to this mod's changes

hill-climb is a skill published in the GitHub repository skillberry-ai/cap-evolve (54 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 2,318 once invoked, about $0.0006 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