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 skills add OutlineDriven/odin-claude-plugin --skill unleak-abstractiongit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/unleak-abstraction)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/unleak-abstraction"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/unleak-abstraction/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.
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/unleak-abstraction"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/unleak-abstraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00044 | $0.01048 |
| Opus 5 | $0.00022 | $0.00524 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
unleak-abstraction 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unleak abstraction
Contract
| Field | Bound contract |
|---|---|
| Trigger | User names an abstraction leak and wants it sealed as a module seam, configuration option, or explicit override, or deliberately exposed as a named boundary. |
| Authority | Reversible local: writes only named local artifacts; rollback is stated before mutating (version control or undo). No remote mutation. |
| Side effect | Refactored code that seals or deliberately exposes the named leak. A wrapper is rejected if it adds more than half the measured complexity of what it hides. |
| Done | The abstraction leak is sealed or deliberately exposed; the complexity gate holds (wrapper complexity is less than half the hidden complexity, or both are zero as the zero-complexity case from step 5), confirmed by post-change re-measurement. |
Inputs
Required:
- The target code containing the abstraction leak (must be supplied by the user).
- The location or symbol name of the leak.
Optional:
- The desired seam, configuration key, or override shape.
- A stated complexity budget or constraint.
Complexity metric
Complexity is measured as branching decisions: the count of if, else if, else, case/match arms, ternary conditionals, and short-circuit logical operators (&&, ||) in conditions that control flow. Each branching decision counts as 1. Linear statements, assignments, and function calls count as 0. This metric is applied identically to the hidden code (the code that conceals the dependency) and the proposed wrapper (the seam, parameter, or configuration surface that replaces it).
Procedure
- Locate the leak and its hidden dependency. Examine the code, identify the hidden dependency, implicit coupling, or encapsulation violation the user wants surfaced. Done when: the leak is located and its hidden dependency, coupling, or violation is identified.
- Confirm the user's intent: seal the leak (make it explicit and controlled) or expose it (name it as a configuration or module seam). Done when: the intent is confirmed as seal or expose.
- Measure the hidden complexity. Count the branching decisions in the code that conceals the dependency or coupling. Record the count as
hidden_complexity. Done when:hidden_complexityis a non-negative integer. - Propose the minimal structural change that achieves the intent: a new parameter, field, configuration entry, module boundary, or override hook. Done when: one minimal structural change is proposed.
- Measure the wrapper complexity. Count the branching decisions in the proposed wrapper or seam code. Record the count as
wrapper_complexity. Compute the ratiowrapper_complexity / hidden_complexity. Ifhidden_complexityis 0, any wrapper with branching decisions is rejected; a zero-complexity wrapper (a pure pass-through or direct exposure) is admitted. Done when: the ratio is computed and the proposal is admitted (ratio < 0.5) or rejected (ratio >= 0.5). - If the proposal is rejected, report the measured ratio and stop. Do not apply. Done when: the rejection is reported.
- Apply the change. If applying requires deleting or relocating code, record the original text for rollback. Done when: the change is applied and original text is recorded for rollback.
- Re-measure the wrapper complexity after the change lands. Confirm the gate still holds: if
hidden_complexityis 0, the wrapper must still have zero branching decisions (the zero-complexity case from step 5); otherwise confirmwrapper_complexity / hidden_complexity < 0.5. Done when: the post-change measurement confirms the gate holds. - Roll back if the done predicate cannot be satisfied; report the rollback and stop. Done when: the rollback is complete or the done predicate is confirmed.
What ships with it
1 file 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 Changed · -29 tokens per session 9e99bcd35a90
- 7d ago First seen · 54 lines · 73 tokens per session scan A 94aeee949bca
unleak-abstraction is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,048 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…