A template for creating a new agent skill, including its trigger description, required inputs, implementation steps, commands, and references. The skill must define real, deterministic behavior and a JSON output contract.

Use it when building a skill package, documenting its inputs and outputs, running its validation check, and executing its scripts.

It gives a skill project a clear structure and checks that required inputs and implementation methods are not missing or fabricated.

<skill-name> — Skill by skillberry-ai

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/skillberry-ai/cap-evolve/skill

Any agent

npx skills add skillberry-ai/cap-evolve --skill skill

Clone the repo

git clone --depth 1 https://github.com/skillberry-ai/cap-evolve

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 499 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.

Model	Per session	Once invoked
Fable 5	$0.00050	$0.00499
Opus 5	$0.00025	$0.00249
Sonnet 5	$0.00010	$0.00100
Haiku 4.5	$0.00005	$0.00050

Measured 2d ago against content hash 06dbe4707b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

<skill-name> 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.

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.

templates/skill/SKILL.md · 47 lines

What it actually says

One-sentence statement of what running this skill accomplishes.

When to use this skill

Concrete triggers. What situation in the pipeline calls for it.

Inputs

Read inputs/INPUTS.md. For every input marked NEEDED that is not already present, ASK THE USER — quote the expected path, the command/options to obtain it, and any alternatives — and do not fabricate it. RECOMMENDED inputs may be skipped, with a logged note.

What you must implement

The optimizer agent implements the abstract methods in scripts/abstract.py (or confirms the project adapter already covers them). Then run scripts/check.py — it refuses until every method is real and deterministic, and tells you exactly what is still stubbed.

How to run

python scripts/check.py        # gate: must pass first
python scripts/run.py <args>   # executes the step; prints a JSON result to stdout

The JSON on stdout is the contract surface — downstream skills (and hosts that can't import Python) consume it directly.

References — load only when you need them

references/concepts.md — grounded background and the reasoning behind the design.
references/examples.md — concrete worked examples.
references/pitfalls.md — failure modes and important points to watch.

Prompt

prompt/PROMPT.md is the prompt template handed to the using-agent when this skill drives a model step. Fill its {{placeholders}} from the inputs.

Files

What ships with it

10 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.

2d ago First seen · 47 lines · 50 tokens per session scan A 06dbe4707b12

Subscribe to this mod's changes

<skill-name> is a skill published in the GitHub repository skillberry-ai/cap-evolve (47 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 499 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.

DSPy agent-optimization agent-skills agentic-ai ai-agents claude

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

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.

microsoft/agent-framework · 65 tokens

<skill-name>