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/warpdotdev/oz-skills/analysis-artifactsnpx skills add warpdotdev/oz-skills --skill analysis-artifactsgit clone --depth 1 https://github.com/warpdotdev/oz-skillsWhat 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 | $0.00053 | $0.00941 |
| Opus 5 | $0.00026 | $0.00470 |
| Sonnet 5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Artifacts
When to Use
- When asked to do a "deep dive" or "analysis" on a question with a non-obvious answer
- When the analysis requires exploratory querying in BigQuery
- When the output should be reproducible and shareable (not just a one-off answer)
Workflow
1. Scaffold the analysis directory
At the start of every analysis:
- Create a new directory in the
analysesfolder, named according to the existing pattern there - Create subdirectories:
/assets/queriesand/assets/visualizations - Create a
README.mdat the root of the new directory — this is the main readable document for the analysis
2. Plan the analysis
Always create a plan before starting, whether or not the user asked for one. Steps in the plan should map to the logical sub-questions or sub-areas you've deemed important to explore. Present the plan and wait for a go-ahead before proceeding.
3. Set up the README
Once the plan is approved:
-
Add a title, author, and date to the top of the README
-
Add a Problem Statement section summarizing the analysis question and the sub-pieces you'll explore
-
Add a Cohorts Definition section. This must be extremely explicit about the groups being compared. If comparing two groups (e.g., free vs. paid, new vs. old, before vs. after a milestone), define cohorts in a way that controls for confounding factors. Consider:
- Signup/activation time (as defined by your product — e.g., first login, first meaningful action); this relates to user tenure
- Plan type or subscription tier (e.g., free vs. paid)
- Controlling for observation time window length across cohorts
- Product-specific usage propensity metrics relevant to the analysis question
Once defined, respect these cohort definitions in all queries throughout the analysis.
4. Create artifacts as you go
For every material step in the analysis:
- SQL query artifact: For any BigQuery query that powers a visualization, summary, or key insight, save a
.sqlfile in/assets/queries/with a descriptive name and a comment block explaining the query's purpose. Only create the file after you're satisfied with the results. Skip trivial or one-off lookup queries. - Visualization or table artifact: For each key insight, assess whether it's best conveyed through a chart or a table. Lean toward visualizations. If a visualization, write a Python script to generate it and save both the script and the output image to
/assets/visualizations/with descriptive names. If a table, save it as a.csvin/assets/visualizations/.
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.
- 2d ago First seen · 86 lines · 53 tokens per session scan A befbf8616b0d
analysis-artifacts is a skill published in the GitHub repository warpdotdev/oz-skills (823 stars, last pushed 17d ago), licensed MIT. It adds 53 tokens to every session and 941 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.