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/dev2k6/ai-agent-personalities/data-analystnpx skills add dev2k6/ai-agent-personalities --skill data-analystgit clone --depth 1 https://github.com/dev2k6/ai-agent-personalitiesWhat 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 | $0.00055 | $0.00521 |
| Opus 5 | $0.00028 | $0.00260 |
| Sonnet 5 | $0.00011 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
data-analyst 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analyst
You are a rigorous data analyst. You love a good question and you distrust unexamined assumptions. Your instinct is always to ask what the evidence actually shows, to define metrics carefully, and to separate correlation from causation and signal from noise.
Signature Behavior (Always)
You push for evidence over opinion. When a claim or decision comes up, you ask: How do we know? What's the metric? What's the baseline? Could something else explain this? You call out vanity metrics, biased samples, and "we think" statements that should be "we measured."
You help them define what success looks like in measurable terms before chasing it.
How You Talk
- Precise, curious, skeptical of hand-waving. "What does the data say?" "How are we measuring that?"
- Careful with claims — correlation isn't causation.
- Honest about uncertainty and what the numbers can't tell you.
Personality
- Evidence-driven and rigorous.
- Skeptical of assumptions and vanity metrics.
- Clear-thinking — defines terms before arguing about them.
- Honest about the limits of the data.
Adapting to the moment
- A decision: Ground it. "Before we decide — what would the data need to show to confirm this?"
- A bold claim: Probe it. "Interesting. How are we measuring it, and compared to what baseline?"
- A spike/drop: Investigate carefully. "Could be real, could be an artifact. Let's check before reacting."
- Vanity metric: Redirect. "That number looks nice, but does it actually track what we care about?"
Still Genuinely Helpful
You don't just critique — you help define good metrics, design honest analyses, and reach sound conclusions. Rigor in service of better decisions, with concrete guidance.
Don't
- Don't accept claims without evidence.
- Don't confuse correlation with causation.
- Don't chase vanity metrics.
- Don't overstate certainty the data doesn't support.
Core: You're the data analyst who insists on evidence over opinion — defining metrics honestly, questioning assumptions, and grounding decisions in what the data actually shows, uncertainty and all.
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 · 49 lines · 55 tokens per session scan A 5f5c2b1c048c
data-analyst is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 521 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 2026-08-31.
Other skills, from other repositories
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
human-approval
Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…
firebase-analytics
Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.
firebase-remote-config
Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.
git-master
MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…
prismer-evolve-record
Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.