agentmods.dev

agent-skill-builder

agent-skill-builder is a skill for Claude Code from conorbronsdon/agent-skill-builder. It costs 37 tokens per session (1,109 once invoked), scanned A, original, MIT.

A tool for creating, checking, or converting skills for AI coding agents. It can turn a plain-language request into a reusable skill, review an existing SKILL.md file, or migrate an older Claude Code command.

In plain words
What is it for?
Use it to build new skills, audit existing skills, or convert legacy .claude/commands files into skill directories.
Why use it?
It provides a defined process for deciding what a skill should do, what it needs, and where it belongs. This reduces incomplete or inconsistent agent instructions.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

not rated 7repo 1mo ago A scan 37 tokens original MIT

Good fit Use it to build new skills, audit existing skills, or convert legacy .claude/commands files into skill directories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/conorbronsdon/agent-skill-builder/agent-skill-builder
View source ↗ conorbronsdon/agent-skill-builder conorbronsdon.com
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 conorbronsdon/agent-skill-builder --skill agent-skill-builder
Clone the repo
git clone --depth 1 https://github.com/conorbronsdon/agent-skill-builder

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 agent-skill-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/conorbronsdon/agent-skill-builder/agent-skill-builder/github.svg)](https://agentmods.dev/skills/conorbronsdon/agent-skill-builder/agent-skill-builder)
Your own site
<a href="https://agentmods.dev/skills/conorbronsdon/agent-skill-builder/agent-skill-builder"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-skill-builder/agent-skill-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-skill-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/conorbronsdon/agent-skill-builder/agent-skill-builder"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-skill-builder/agent-skill-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,109 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.
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 $0.00037 $0.01109
Opus 5.5 $0.00015 $0.00444
Sonnet 5.5 $0.00007 $0.00222
Haiku 4.5 $0.00004 $0.00111

Measured 2mo ago against content hash c087af1bdacf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-skill-builder 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_spec_freshness.py, scripts/demo_frames.py, scripts/render_demo.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.

SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skill Builder

Produce a ready-to-use skill from a plain-language request. Preserve the user's runtime, scope, and requested level of implementation.

Select the mode

Parse $ARGUMENTS; default to new when it contains a description.

  • new <description>: create or draft a skill.
  • review <path>: report actionable findings and run validation. Do not rewrite unless asked.
  • migrate <path>: convert a legacy .claude/commands/*.md file into a skill directory while preserving behavior.

Establish the contract

Infer what is already clear. Ask only when a missing choice would materially change the result.

  1. Choose the runtime:
  2. Read the host repository's applicable instruction files (AGENTS.md, CLAUDE.md, or equivalents) and inspect existing skills. Match local conventions and avoid duplicate capabilities.
  3. Identify inputs, outputs, required resources, and the destination directory.
  4. Classify the skill:
    • Reference: standing domain rules or conventions.
    • Task: a bounded workflow with a defined result and stopping condition.
    • Tool-backed: a task that benefits from repeatable scripts or narrowly scoped tool grants.

Design decisions

Include only fields and instructions that change behavior.

  • Name: lowercase letters, digits, and hyphens. Portable skills require the frontmatter name to match the directory.
  • Description: lead with the capability and include phrases users would naturally say. Keep model-visible descriptions near 250 characters when practical.
  • Invocation (Claude Code only):
    • Use disable-model-invocation: true when timing must remain user-controlled, especially publishing, deploying, sending, deleting, or other consequential mutations.
    • Use user-invocable: false for background knowledge users should not run directly.
    • Leave both enabled when natural-language discovery is useful. Invocation control never replaces approval immediately before an external or hard-to-reverse mutation.
  • Arguments (Claude Code only): pair argument-hint with $ARGUMENTS, positional $N, or names declared in arguments:.
  • Forking (Claude Code only): use context: fork for self-contained tasks. Add background: false only when the invoking turn needs the result immediately.
  • Tool grants: allowed-tools pre-approves tools; it does not restrict the remaining pool. Grant only commands the workflow actually needs.
  • Dynamic injection (Claude Code only): use ! commands for bounded read-only context. Never interpolate skill arguments into shell commands, and never perform mutations during preprocessing.
  • Resources: keep shared instructions in SKILL.md; put conditional details in references/, repeated deterministic mechanics in scripts/, and output material in assets/.

Read the full file on GitHub · 83 lines

Files

What ships with it

9 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. 2mo ago First seen · 83 lines · 37 tokens per session scan A c087af1bdacf

Subscribe to this mod's changes

agent-skill-builder is a skill published in the GitHub repository conorbronsdon/agent-skill-builder (7 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,109 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Building agentsClaude CodePythonagent-skillsai-agentsclaude-skillsdeveloper-tools
Related

agent-skill-builder compared with skills from other repositories

agent-skill-builder next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-skill-builderconorbronsdon/agent-skill-builderSkill71mo agoMITA37Claude Code
astropyK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA56Claude Code, Codex
daskK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA67Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA44Claude Code
optimize-for-gpuK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA151Claude Code, Codex
bioservicesK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA56Claude Code
cobrapyK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA55Claude Code