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/product-proof-stage/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/product-proof-stage)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/product-proof-stage"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/product-proof-stage/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/product-proof-stage"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/product-proof-stage.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 | $0.00077 | $0.00253 |
| Opus 5.5 | $0.00031 | $0.00101 |
| Sonnet 5.5 | $0.00015 | $0.00051 |
| Haiku 4.5 | $0.00008 | $0.00025 |
Grade A, and why
product-proof-stage 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 1mo 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
product-proof-stage
Entry point for the Tell-adapted product-proof workflow skill.
Full playbook: agent-skills/web-design/premium-content-custom-web/product-proof-stage/SKILL.md
Quick contract
- Mechanism before claims — product panel is the evidence
- States: input → process → draft → review → approve (human gate; never auto-apply)
- Declared features only; label
Sample workflowwhen not live - HTMX stage swaps for progressive panels; static first frame always complete
- Taste Controls + aesthetic lean codes; dogfood Tell detectors
- Prefer
designFromFeatures— layoutworkflow-proofonsaas-marketing
After generate
If Tell is available: capture the preview → diagnose → fix any generic tells before handoff.
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.
- 1mo ago First seen · 24 lines · 77 tokens per session scan A a43ccd477310
product-proof-stage is a skill published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 77 tokens to every session and 253 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
next-action
Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
am-command-ponytail-audit
Audit the whole repo for over-engineering, what can be deleted.
autonomous-lead
Autonomous implementation workflow for low-supervision execution with mandatory decision logging. Executes end-to-end without interactive approval gates, but persists auditable run logs and architecture decisions in project artifacts. Use when the developer asks for autonomous mode, low supervision, or unattended…
spec-creator
Creates implementation-ready specs from brief descriptions, existing markdown requirements, or prior specs. Adapts the ticket-creator workflow to spec-engineering with structured lifecycle states, execution planning, and quality gates. Use when creating or refining specs under .agent-runway/specs.
express
Minimal-friction implementation path for well-scoped tasks. Assumes the developer has full context, knows the codebase, and does not need planning ceremony. Use when the developer says "/express", wants to move fast on a well-understood single-layer change, or explicitly opts out of the full workflow.
refactor
Guides structured refactoring to improve readability, maintainability, and SOLID/Clean Architecture alignment — without changing observable behaviour. Deepest examples are in .NET/C#, but the workflow applies to any stack. Use when the user says "/refactor", "clean up", "improve this", "simplify", "restructure"…