Borrowing it
Nothing to install: this file belongs to ashishpatill/tell-proof. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ashishpatill/tell-proof/master/.cursor/skills/tell-user-session-learn/SKILL.mdgit clone --depth 1 https://github.com/ashishpatill/tell-proofWrote 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/ashishpatill/tell-proof/tell-user-session-learn)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-user-session-learn"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-user-session-learn/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/ashishpatill/tell-proof/tell-user-session-learn"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-user-session-learn.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 | $0.00040 | $0.00354 |
| Opus 5 | $0.00020 | $0.00177 |
| Sonnet 5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
tell-user-session-learn 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 6d 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.
What it actually says
tell-user-session-learn
End-user loop (browser / local machine). Makes Tell better for this user across sessions.
This is not the developer corpus loop (agency-run-learn + research/design-data.local.json).
| Loop | Who | Where | Improves |
|---|---|---|---|
| User session | Ashish (product user) | localStorage tell:user-design-profile |
His directions, priorities, tools |
| Dev corpus | Tell maintainer | TELL_DESIGN_DATA / design-data.local.json |
Shared engine memory, gates, seeds |
What is remembered (user machine only)
- Preferred art-direction preset
- Recent voice/text phrases + action categories → priority weights
- Soft bans from phrases ("no purple", "less shadow")
- Tool prefs (voice, MCP, live capture)
Schema: UserDesignProfile in @tell/schema
Lib: apps/web/src/lib/user-session-learn.ts
Rules
- Never write user profiles into the Tell git repo or design-data checkout.
- Never upload user profiles unless the product later adds an explicit account sync.
- Developer corpus must stay gated (
isDevCorpusEnabled) — no Vercel/public demo pulls.
Agent prompt
Use tell-user-session-learn when changing how Tell remembers a founder's taste.
Keep developer design-data learning separate (agency-run-learn + design-data.README).
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.
- 6d ago First seen · 39 lines · 40 tokens per session scan A 5a6fe38f6164
tell-user-session-learn is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 14d ago), licensed MIT. It adds 40 tokens to every session and 354 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
app-ui-design
Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.
product-ux-expert
Product interaction and UX expert. Use when reviewing UI/UX, conducting heuristic evaluations, designing user journeys, applying cognitive psychology principles, or ensuring WCAG 2.2 accessibility compliance.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
help-flow
Help about Rosetta: explains capabilities and usage.
app-user-story-qa
End-to-end app feature inventory and user-story testing workflow with a canonical tracker. Use when the user asks to audit every feature, derive expected behavior from code, test user journeys, or explicitly fix and retest documented UX or logistical defects.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.