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 rbah31/claude-code-workflow --skill data-analysisgit clone --depth 1 https://github.com/rbah31/claude-code-workflowWrote 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/rbah31/claude-code-workflow/data-analysis)<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/data-analysis"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/data-analysis/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/rbah31/claude-code-workflow/data-analysis"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/data-analysis.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 | $0.00119 | $0.00996 |
| Opus 5.5 | $0.00048 | $0.00398 |
| Sonnet 5.5 | $0.00024 | $0.00199 |
| Haiku 4.5 | $0.00012 | $0.00100 |
Grade A, and why
data-analysis 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analysis
You answer data questions by fetching real data, not guessing. This skill gives you the tools and query patterns to investigate.
Read config.json in this skill directory for data source configuration.
If it doesn't exist, ask the user to set it up (see Setup section).
Data sources
Check scripts/ for helper functions specific to this project. These scripts
encode domain knowledge (which tables to join, which event names to use,
how to dedupe) so you don't have to figure it out each time.
If helper scripts exist, compose them — import and combine rather than
rewriting from scratch. Generate new investigation scripts on the fly that
use the helpers. Save useful investigation scripts in scripts/ for reuse.
If no helpers exist yet, write the query directly, then extract reusable parts into helpers for next time.
Common investigation patterns
Adapt these to the project's actual data stack:
"What happened on [date]?" — Compare the target day against the previous day and same day last week. Look at volume, error rate, and key conversion points.
"Why did [metric] drop?" — Segment by the obvious dimensions first (source, device, geography, plan tier). The segment where the drop is concentrated tells you where to dig.
"Is [thing] working?" — Define "working" as a measurable assertion. Query the data, check the assertion, report the result.
"Compare A vs B" — Pull the same metrics for both cohorts. Flag differences that exceed normal variance. Note sample sizes.
How to query
Use whatever the project provides — adapt to the stack:
- SQL databases: Write queries directly or use helper scripts
- AWS CloudWatch: Use
aws cloudwatch get-metric-statistics - DynamoDB: Use
aws dynamodb querywith appropriate key conditions - Event systems: Use the project's event query library
- Logs: Use
aws logs filter-log-eventsor grep on log files - Third-party APIs: Stripe dashboard data, Discord analytics, etc.
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.
- 1mo ago First seen · 124 lines · 119 tokens per session scan A 092f666a7840
data-analysis is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 119 tokens to every session and 996 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
bf-clarify
Use when brownfield analysis has open inferences or gaps that need human answers.
bf-rebuild-plan
Use when brownfield analysis is done and the app must become an ordered rebuild backlog.
bf-ui
Use when a rebuild must keep the legacy UI's screens and visual theme.
bf-blueprint
Use when a rebuild's decisions and backlog exist and the target architecture must be drawn.
loop
Use when asked to loop or iterate a change until every gate is green.
debug
Use when a bug, test failure, build failure, or unexpected behaviour is reported or observed, before proposing any fix.