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/outlinedriven/odin-claude-plugin/analysis-artifactsnpx skills add OutlineDriven/odin-claude-plugin --skill analysis-artifactsgit 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/analysis-artifacts)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/analysis-artifacts"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/analysis-artifacts.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 5.1 | $0.00068 | $0.00990 |
| Opus 5 | $0.00034 | $0.00495 |
| Sonnet 5 | $0.00014 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
analysis-artifacts 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.
This is a copy
100% identical to analysis-artifacts — 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis artifacts
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks for a deep dive, exploratory analysis, or data analysis on BigQuery data |
| Authority | Reversible local writes to a dated analyses tree; warehouse reads proceed only after the user approves the analysis plan |
| Side effect | Creates a dated analyses/-/ directory containing README.md, assets/queries/.sql, and assets/visualizations/.{png,svg,html}; overwrites stale artifacts in the same directory consistently |
| Done | README contains the approved plan, explicit cohort definitions, links to every SQL and visualization file, a TLDR, and key takeaways; source_paths are documented |
Inputs
- Analysis request (required): the question or hypothesis to explore against BigQuery data.
- BigQuery project and dataset (required): the warehouse target for read queries.
- Date (required): a calendar date in YYYY-MM-DD format used to construct the analysis directory path.
- Analysis name (required): a short slug used for the directory name under analyses/.
- Cohort definitions (derived): population filters expressed as SQL predicates and stated explicitly in the README before any query runs.
- Existing analyses tree (optional): prior artifacts that may need to be overwritten.
Procedure
- Draft a written analysis plan that states the question, BigQuery project and dataset, cohorts to compare, queries to run, and visualizations to produce. Present the plan to the user and stop until the user explicitly approves it. Do not run warehouse queries before approval. Done when: the plan is presented and user-approved.
- After approval, create analyses/-/ with the subdirectories assets/queries/ and assets/visualizations/. Done when: the directory and subdirectories exist.
- Save each SQL query as a standalone assets/queries/*.sql file. Every query must run independently against the named BigQuery project and dataset. Done when: each query is a standalone .sql file.
- Run the approved queries against BigQuery in read mode. Record each query's source path in the README. Done when: each query's source path is recorded in the README.
- For each result set that warrants a visualization, produce a PNG, SVG, or HTML file under assets/visualizations/. Name the file after its originating query. Done when: each visualization file is named after its originating query.
- Write README.md in the analyses/-/ root with these sections in order: TLDR, Key Takeaways, Approved Plan, Cohort Definitions, Queries (with links to each assets/queries/.sql file), Visualizations (with links to each assets/visualizations/ file), and Source Paths. Done when: README links every SQL and visualization file, states cohort definitions, includes TLDR and key takeaways, and documents source_paths.
- If analyses/-/ already contains stale artifacts, overwrite the affected files in place so the directory matches the current approved plan. Do not leave mixed old and new versions of the same artifact. Done when: the directory matches the current approved plan with no mixed versions.
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.
- yesterday First seen · 41 lines · 68 tokens per session scan A 41f2a36611fc
analysis-artifacts is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 990 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to analysis-artifacts, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
craft-goal
Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment's intent routes to plan.).
cloudflare-vectorize
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
cloudflare-workers-ai
Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AIERROR, rate limits, token exceeded errors.
human-only-skills
Name the skills reserved for people to invoke — where the runtime honors disable-model-invocation — and when to reach for each. Triggers: "human-only skills", "which skills must I run myself".
nano-banana-prompting
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…