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/theogbrand/yoink/decomposenpx skills add theogbrand/yoink --skill decomposegit clone --depth 1 https://github.com/theogbrand/yoinkWrote 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.
[](https://agentmods.dev/skills/theogbrand/yoink/decompose)<a href="https://agentmods.dev/skills/theogbrand/yoink/decompose"><img src="https://agentmods.dev/badge/skills/theogbrand/yoink/decompose.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00026 | $0.01094 |
| Opus 5 | $0.00013 | $0.00547 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
decompose 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose
Do not invoke this skill unless explicitly requested. It is called by
/yoink:yoinkor run standalone by the user.
Prerequisite: /yoink:curate-tests must have been completed first.
Seed the decomposition queue with the target package:
uv run python ${CLAUDE_SKILL_DIR}/scripts/decomp.py enqueue <PACKAGE_NAME>
Then run the decomposition loop below until the queue is empty.
Decomposition Loop
Begin loop. Repeat until the queue is empty.
1. Dequeue
uv run python ${CLAUDE_SKILL_DIR}/scripts/decomp.py dequeue
- If queue is empty then decomposition complete, remove the real library and stop.
uv remove <PACKAGE_NAME>
2. Evaluate
Use the yoink:decomp-evaluator agent to evaluate whether the dequeued library should be kept or decomposed.
Pass input as JSON:
{
"library_name": "<DEQUEUED_LIBRARY>",
"package_name": "yoink_<PACKAGE_NAME>"
}
- If Keep then go back to step 1.
- If Decompose then continue to step 3 with the evaluation output.
3. Prepare the sub-package for the implementer agent
Complete these steps IN ORDER before entering the loop.
Exception: When the dequeued item is
{original_package}(the first item in the queue), skip steps 3a–3c and go straight to 3d. Baseline verification (3a) was already completed by/yoink:curate-tests, scaffolding (3c) was already done by/yoink:setup, and import rewriting (3b) is a no-op for the original package since there are no sub-package imports to rewrite yet.
a. Verify baseline
Run the top-level generated tests:
uv run ${CLAUDE_PLUGIN_ROOT}/scripts/run_tests.py --project-dir . 2>&1
- If all tests pass then proceed to step b.
- If any test fails then the baseline is broken and must be fixed before proceeding. Investigate the test failures, fix the issues, and re-run the tests until they all pass.
b. Rewrite imports
Swap {sub_package} imports in yoink_{top_package}/ source code to point at yoink_{sub_package}:
What ships with it
2 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.
- 5d ago First seen · 127 lines · 26 tokens per session scan A d04ee3146659
decompose is a skill published in the GitHub repository theogbrand/yoink (35 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,094 once invoked, about $0.0001 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
supply-chain-review
When the user asks about dependency security, supply chain hardening, or wants to review the safety of their installed packages, use this skill.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
cesiumjs-camera
CesiumJS camera control - Camera, flyTo, lookAt, setView, ScreenSpaceCameraController, CameraEventAggregator, flight animation. Use when positioning the camera, creating flyTo animations, constraining user navigation, tracking entities, or converting between screen and world coordinates.
cesiumjs-core-utilities
CesiumJS core utilities and networking - Resource, Color, Event, Request, RequestScheduler, error handling, helper functions, feature detection. Use when fetching remote data, managing HTTP requests, working with colors, handling events, debugging errors, or using utility functions like defined, clone, or…