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 damianvtran/local-operator --skill data-analysisgit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/data-analysis)<a href="https://agentmods.dev/skills/damianvtran/local-operator/data-analysis"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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/damianvtran/local-operator/data-analysis"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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 | $0.00045 | $0.00623 |
| Opus 5.5 | $0.00018 | $0.00249 |
| Sonnet 5.5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data analysis
Numbers that survive scrutiny: profile first, keep queries reproducible, carry provenance, sanity-check the result.
Profile before trust
| Check | Why it matters |
|---|---|
| Shape: rows, columns, time range | Know what you have before asking questions of it |
| Types and units per column | A text date, or cents read as dollars, corrupts every downstream number |
| Keys and duplicates | Duplicate keys silently change every aggregate |
| Missingness per column | Null-heavy columns change what a rate means |
| Distributions and ranges | Outliers and impossible values (negative ages, future dates) surface here |
| Timezone and calendar of timestamps | Day boundaries move with zones |
Keep the profile as a small set of queries you can rerun, not ad-hoc typing.
Reproducible queries
- Keep the exact query behind every number in the report. A number nobody can re-derive is a rumour.
- Deterministic: pin the snapshot or time window, make ordering explicit before any limit, and avoid "latest row" ambiguity.
- Work in steps; save intermediates. After changing an input, rerun the step rather than mentally adjusting its output.
Guard silent joins and filters
- Count rows before and after every join. An inner join on an incomplete key drops rows without an error.
- Check filter semantics: inclusive or exclusive bounds, null membership, timezone edges. Apply each filter once.
- State the population: "of the 4,210 rows matching X" beats "of the data".
Provenance and checks
- Every reported number carries its source (table, snapshot), filter, and derivation. Derive it, or say where it came from.
- Reconcile: totals equal the sum of their parts; an independent cut of the same data reproduces the number.
- Units on everything: counts, rates, currency. Percentages name their denominator. Magnitudes are checked against expectation; a 1000x jump is a units or join error until proven otherwise.
- Small n: below your stated threshold, report the count, not a rate. "60% (n=5)" misleads; "3 of 5" does not.
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.
- 5d ago First seen · 54 lines · 45 tokens per session scan A 67c8d23cbff9
data-analysis is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 623 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
coding-standards
Applies language-neutral engineering standards when writing or reviewing code, especially around boundaries, failures, domain models, dependencies, tests, and type safety.
domain-modeling
Maintains project domain language, context maps, diagrams, and architectural decisions under ai-artifacts. Use when clarifying terminology, bounded contexts, or durable design decisions.
setup-goal
Turns an idea into an approved goal package under ai-artifacts. Use when work needs clarified intent, scope, accepted facts, an implementation plan, and an explicit handoff.