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 load-bearing-assumption-testgit 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/load-bearing-assumption-test)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/load-bearing-assumption-test"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/load-bearing-assumption-test/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/load-bearing-assumption-test"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/load-bearing-assumption-test.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 | $0.00035 | $0.00619 |
| Opus 5 | $0.00017 | $0.00309 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
load-bearing-assumption-test 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load-bearing assumption test
Contract
| Field | Bound contract |
|---|---|
| Trigger | User says "tell me why this is wrong", or "poke holes in this" about a plan, design, or claim |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output only: a single root objection and first-nail recommendation as { root, first_nail }; no files written |
| Done | Root is genuinely load-bearing and the first nail is the cheapest experiment beating the plan or null when none exists |
Inputs
The plan, design, or claim under attack, supplied by the user in the conversation. No file or remote input is required; the skill reads only what the user presents.
Procedure
- Pin the load-bearing assumption: identify the single thing that must hold for the whole plan to stand. Done when: one assumption is named whose failure collapses the plan.
- Attack on whatever axes apply: a fact that may be false, confabulation, analogy mistaken for isomorphism, a future-tense suture, or the sharpest one, a principle cited but its opposite implemented. For empirical plans, also leakage and statistical power or family-wise error. Done when: every applicable axis has been tested against the pinned assumption.
- Collapse to one root: the single objection whose failure makes the rest moot. Not a list. Done when: one root objection is selected, not a register of objections.
- Find the first nail: the cheapest falsification available before the expensive program runs. Done when: one experiment is named that is cheaper than the plan and would prove whether root matters, or null is returned when no such experiment exists.
- Return { root, first_nail }. Nothing else. Done when: the pair is returned and no additional objections or scaffolding are appended.
Failure and recovery
- No load-bearing assumption found: state that the plan has no single point of failure and return the sharpest objection found, labeled as non-root. Do not fabricate a root.
- No cheaper first nail exists: return the root with first_nail set to null and state that no falsification is cheaper than running the plan. Do not invent an experiment.
- Never widen to a risk register or a list of objections; that is a different contract. If the user asks for more than one objection, stop and name the scope mismatch.
- Never swallow the absence of a root by pretending the done predicate holds.
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 First seen · 38 lines · 35 tokens per session scan A ff939f388d67
load-bearing-assumption-test is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 619 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 2026-09-06.
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…