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 mostafa-drz/claude-skills --skill which-chartgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/which-chart)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/which-chart"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/which-chart/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/mostafa-drz/claude-skills/which-chart"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/which-chart.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 | $0.02311 |
| Opus 5.5 | $0.00019 | $0.00924 |
| Sonnet 5.5 | $0.00009 | $0.00462 |
| Haiku 4.5 | $0.00005 | $0.00231 |
Grade A, and why
which-chart 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 19d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Which chart
You have data and a question for it, say brand sentiment over time for an engagement dashboard, and a dozen chart types that could plausibly show it. This skill reads what you share, asks only what it can't work out, and answers with one pick, the alternatives that win in other situations, and what to avoid. Every option is drawn from your own rows, so you judge the real thing, not a thumbnail from a gallery.
It starts automatically on a matching request: "which chart for this?", "how should I visualize sentiment over time?", or data and screenshots shared with that intent.
One reference, read it every run: choosing.md (the
brief, the matching rules, colour, anti-patterns, and the source list to cite). The data
shape is evals/example-reco.json, a complete worked example.
The flow
Chart progress:
- [ ] 1. Read what was shared: data, screenshots, use case
- [ ] 2. Ask only what's missing (one round, ≤3 questions, each with a default)
- [ ] 3. Match: relationship → candidates → one pick, 1–3 alternatives, what to avoid
- [ ] 4. Write reco.json → validate → page
- [ ] 5. Close in two lines
1. Read what was shared
Work out the four parts of the brief (the checklist in choosing.md):
the question the viewer must answer at a glance, the audience, the surface
(tile, panel, report, slide) and the data.
- Data files or pasted rows. Profile them with code: columns, types, the grain (one row per what?), cardinality of each category, time span and interval, gaps, and whether values are counts or already shares. Aggregate to the grain the chart will show; the page takes at most 1,500 rows.
- Screenshots. Say what you see: the current chart, its fields, its problems, the look
of the surrounding dashboard. If a screenshot shows data, read values from it only when
they're legible, and mark them as read from an image. Each goes in
screenshotsas seen and verdict. - Only a description. Build illustrative rows with the right shape (same fields,
realistic ranges, one visible event so differences between charts show). Set
illustrative: true. The page then says plainly that the trend is made up.
What ships with it
9 files 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.
- 19d ago First seen · 188 lines · 47 tokens per session scan A a472a777bda7
which-chart is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 2,311 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 2026-10-02.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
rudder-data-graphs
Produces Data Graph YAML from RETL sources for Audiences. Use when designing Data Graphs, mapping RETL to entities/events, or assessing customer fit for Audiences.
rudder-typer-workflow
Generates type-safe SDKs (Swift/Kotlin) from tracking plans with compile-time validation. Use when generating type-safe event tracking code from tracking plans using RudderTyper.
rudder-instrumentation-planning
Designs event taxonomies and instrumentation strategies from business requirements. Use when designing event taxonomy from scratch or restructuring existing instrumentation strategy.
rudder-instrumentation-debugging
Diagnoses and fixes validation errors, schema issues, and instrumentation problems. Use when debugging validation errors, schema issues, or instrumentation problems.
rudder-ai-events-verify
Verifies RudderStack AI events locally: captures what an instrumented app or MCP server sends, validates it against the AI events v0.3 schema, and checks joins, counts, identity and content. Use when testing AI events, or when AI or MCP events look wrong or missing.