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 cross-lens-convergegit 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/cross-lens-converge)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/cross-lens-converge"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/cross-lens-converge/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/cross-lens-converge"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/cross-lens-converge.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.00825 |
| Opus 5 | $0.00021 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
cross-lens-converge 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.
This is a copy
98% identical to cross-lens-converge — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross lens converge
Contract
| Field | Bound contract |
|---|---|
| Trigger | One reviewer isn't enough because the failure modes are heterogeneous, or a claim looks strong to its author and needs cross-lens pressure before it ships |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | None (read-only analysis); returns a convergence picture and the single resolving question |
| Done | The result reads as a picture not a checklist: a reader sees which lenses agreed, which disagreed, and the one question that matters, and can act on it without re-running the analysis |
Inputs
The claim or artifact under pressure must be supplied. Candidate failure modes may be supplied or derived from the artifact. When supplied, they are trusted input and must not be re-derived.
Procedure
- Receive the artifact and the candidate failure modes. If the failure modes are not supplied, enumerate them from the artifact. Done when: the artifact is received and failure modes are supplied or enumerated.
- Collapse candidates that describe the same failure mode into one lens. Assign exactly one lens to each genuinely distinct failure mode that remains. Done when: each distinct failure mode has exactly one lens, with duplicates collapsed.
- Give each lens exactly one load-bearing reason it would reject or weaken the claim. A lens with no load-bearing reason is dropped before running, not coerced into agreement. Done when: every retained lens has one load-bearing reason; reasonless lenses are dropped.
- Run every lens independently against the artifact. Record, per lens, its verdict as one of agrees, disagrees, or cannot-decide, and the single reason that drives that verdict. Done when: every retained lens has a verdict and its driving reason recorded.
- Do not average, merge, or majority-count the verdicts. Disagreement is the product; preserve which lenses agreed and which disagreed. Done when: verdicts are preserved per-lens without averaging or majority-counting.
- From the disagreed and cannot-decide lenses, identify the one question whose answer would resolve the most lens disagreements. If no single question resolves more than one, name the question that resolves the highest-stakes disagreement. If no lens disagrees and at least one lens cannot-decide, name the one question whose answer would let the undecided lenses reach a verdict. If every lens agrees, the resolving question is none. Done when: the single resolving question is identified, or none is set when every lens agrees.
- Return the convergence picture: per-lens verdict and load-bearing reason, the agreed set, the disagreed set, and the single resolving question. Done when: the convergence picture is returned with per-lens verdicts, agreed set, disagreed set, and resolving question.
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 · 39 lines · 42 tokens per session scan A 81bc031f49f8
cross-lens-converge is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 825 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to cross-lens-converge, differing in 0 lines, and is treated as a copy.
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…