external-skill-fixture-builder

external-skill-fixture-builder is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 34 tokens per session (319 once invoked), scanned A, original, MIT.

A test-fixture builder for patterns from outside ecosystems, such as skill files, plugin manifests, Cursor rules, MCP configurations, or multi-agent workspaces. Fixtures are small test examples, not live dependencies.

In plain words
What is it for?
Use it to create synthetic or pinned fixtures, define expected classifications and risks, and add a check proving the fixture is tested.
Why use it?
It lets a skill-harness test how external patterns are parsed or classified without installing or adopting those systems. It also keeps third-party files out of live caches and user directories.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

Good fit Use it to create synthetic or pinned fixtures, define expected classifications and risks, and add a check proving the fixture is tested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/external-skill-fixture-builder
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 45ck/skill-harness --skill external-skill-fixture-builder
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

Made for: Claude Code, Codex.

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 external-skill-fixture-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/external-skill-fixture-builder.svg)](https://agentmods.dev/skills/45ck/skill-harness/external-skill-fixture-builder)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/external-skill-fixture-builder"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/external-skill-fixture-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 319 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 $0.00034 $0.00319
Opus 5 $0.00017 $0.00160
Sonnet 5 $0.00007 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured 8d ago against content hash 84b5413bcd22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

external-skill-fixture-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 8d 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.

packs/agent-operating-skills/skills/external-skill-fixture-builder/SKILL.md · 43 lines

What it actually says

External Skill Fixture Builder

Use this skill when a third-party ecosystem pattern should be tested by skill-harness but should not become a live dependency.

Process

  • Choose the fixture lane by install posture, not by brand:
    • pure SKILL.md pack
    • plugin manifest
    • Cursor .mdc rules
    • Codex/Claude/Cursor subagents
    • MCP/tool config
    • generated record/replay skill
    • Beads or task-memory repo
    • multi-agent workspace layout
  • Use minimal synthetic fixtures when possible.
  • Use pinned external snapshots only when real structure matters and license/provenance allows it.
  • Keep fixtures out of global user directories and live install caches.
  • Make the fixture assert one behavior: parse, classify, trust recommendation, drift detection, render target, or installer opt-in.
  • Add a command or check that proves the fixture is exercised.

Output

Fixture Lane

Source Or Synthetic Basis

Files Included

Expected Classification

Risk Flags Expected

Check Command

Follow-Up Adoption Question

Avoid

  • making fixtures large mirrors of public repos
  • using fixtures as a back door for third-party adoption
  • mixing fixture coverage with default installer behavior
  • storing credentials, real traces, browser recordings, or private task state in fixtures
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 · 43 lines · 34 tokens per session scan A 84b5413bcd22

Subscribe to this mod's changes

external-skill-fixture-builder is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 319 once invoked, about $0.0002 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

do-it-verify

Use when selecting evidence for a delivery claim, regression fix, installation, or branch closeout.

tdwhere123/do-it · 24 tokens

bug-fixing

Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.

ComposioHQ/composio · 63 tokens

python-testing

Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.

ComposioHQ/composio · 62 tokens

typescript-providers

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.

ComposioHQ/composio · 70 tokens

typescript-sdk

Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must…

ComposioHQ/composio · 67 tokens

typescript-testing

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.

ComposioHQ/composio · 65 tokens