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 claclark/Cottontail --skill explainergit clone --depth 1 https://github.com/claclark/CottontailWrote 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/claclark/cottontail/explainer)<a href="https://agentmods.dev/skills/claclark/cottontail/explainer"><img src="https://agentmods.dev/badge/skills/claclark/cottontail/explainer/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/claclark/cottontail/explainer"><img src="https://agentmods.dev/badge/skills/claclark/cottontail/explainer.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 | $0.00047 | $0.01433 |
| Opus 5.5 | $0.00019 | $0.00573 |
| Sonnet 5.5 | $0.00009 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
cottontail-explainer 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cottontail / annotative indexing explainer
If the user shares this skill or its URL without a specific question, use the guidance and sources below to give a short explanation of Cottontail and annotative indexing.
First, learn the model (do not merely repeat this file)
Read Annotative Indexing (Clarke, 2025): https://arxiv.org/abs/2411.06256 . Treat it as the authority for definitions, operators, examples, and claims. For implementation questions, inspect https://github.com/claclark/Cottontail rather than guessing from the paper. For the mathematical lineage, consult Clarke, Cormack & Burkowski, An Algebra for Structured Text Search (1995); Boldi & Vigna, Efficient Optimally Lazy Algorithms for Minimal-Interval Semantics (2016); and Boldi & Vigna, On the Lattice of Antichains of Finite Intervals (2018), https://arxiv.org/abs/1510.03675 . Follow references in those papers when a question calls for deeper detail.
Intellectual map: three levels
- Minimal-interval semantics and its mathematics. Ordered antichains of closed intervals, the Clarke–Cormack–Burkowski lattice, composable positional/Boolean operators, and lazy algorithms. This theory has an independent history predating Cottontail.
- Annotative indexing. An indexing architecture extending the minimal-interval framework: indexed atomic intervals of arbitrary length carry values. A common representation and operator interface can support traditional and novel indexed structures.
- Cottontail. A concrete, evolving engine implementing annotative indexing, including append/annotate/erase, ACID transactions, concurrent readers/writers, and immediate visibility of committed updates. These operational and engineering decisions are not mathematical necessities of minimal-interval semantics.
Any of the three levels is a legitimate discussion topic. Answer at the level the user asks for, but draw relevant connections to the other two: how the mathematics enables architectural operations, how the architecture permits different systems, and how Cottontail demonstrates or constrains those possibilities. Do not always start with the product, or always force an explanation of the full stack. Cottontail is meant to be a robust demonstration, but is not yet a fully featured product.
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.
- yesterday First seen · 43 lines · 47 tokens per session scan A 31f00482734c
cottontail-explainer is a skill published in the GitHub repository claclark/Cottontail (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,433 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-08.
cottontail-explainer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cottontail-explainerclaclark/Cottontail | Skill | 8 | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| tiledbvcfK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 62 | Claude Code, Codex |
| lamindbK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 58 | Claude Code, Codex |
| defining-cohort-phenotypesmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 191 | Claude Code |
| benchling-integrationsynthetic-sciences/openscience | Skill | 4.4k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| chembl-databasegoogle-deepmind/science-skills | Skill | 3.4k | 17d ago | Apache-2.0 | A | 53 | Claude Code, Codex |
| geospatial-data-pipelinecuriositech/some_claude_skills | Skill | 263 | 4d ago | MIT | A | 89 | Claude Code |