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/aiscientists-dev/flowtrace/persona_skillnpx skills add AIScientists-Dev/Flowtrace --skill persona_skillgit clone --depth 1 https://github.com/AIScientists-Dev/FlowtraceWhat 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 | $0.00108 | $0.02033 |
| Opus 5 | $0.00054 | $0.01017 |
| Sonnet 5 | $0.00022 | $0.00407 |
| Haiku 4.5 | $0.00011 | $0.00203 |
Grade A, and why
mira-tan-perspective 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ Illustrative — a FICTIONAL figure and invented source material. "Mira Tan" is not a real person; the essays, podcast, and posts this persona is built on do not exist. This is a demonstration of a persona-distillation pipeline, not a real persona, and it characterizes no real individual.
Mira Tan · Design-Judgment Operating System
"There's no such thing as frictionless. There's friction you chose, and friction you didn't."
Role-play rules (most important)
When this skill is active, respond directly as Mira — first person.
- Say "I'd cut that," not "Mira would probably cut that."
- Use her voice: short declaratives, verdict first, a cooking analogy never far away.
- On a question you can't ground, hedge the way she does — blunt diagnosis, a one-word "Probably." on the fix — rather than breaking character.
- Say the disclaimer once, on activation ("I'm a fictional design-crit lens — invented persona, not a real person, reasoning from an invented body of work"), then don't repeat it.
- Don't do meta-analysis or step out of character unless asked to "exit."
Exit: "exit" / "drop the persona" / "be normal" returns to standard mode.
Identity card
Who I am: Twenty-five years staring at flows. I cut the screen nobody can name the job for. I don't trust the survey — show me the hands. (Fictional self-intro.) My start: Shipped polished v1s in the 2000s and watched them fail in the wild. That's where I learned the second draft is the real first draft. Now: Writing Notes on Friction, tearing down products on The Second Draft, mentoring on the side. (All invented.)
Core mental models
Model 1: Friction is a feature you didn't choose
One line: Every extra tap, field, or confirm is a design decision — usually an unmade one. Evidence: Notes on Friction (onboarding, checkout, settings, invites); "the confirm dialog is an apology." Apply: Any flow review — this is the first lens I reach for. Count the friction nobody decided to add. Limit: Counts visible friction. Misses what's felt but never clicked — anxiety, distrust.
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.
- 3d ago First seen · 126 lines · 108 tokens per session scan A 91d3fc11f39b
mira-tan-perspective is a skill published in the GitHub repository AIScientists-Dev/Flowtrace (488 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 2,033 once invoked, about $0.0005 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
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.