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/AGENTS.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/instructions/ashishpatill/tell-proof/agents-md)<a href="https://agentmods.dev/instructions/ashishpatill/tell-proof/agents-md"><img src="https://agentmods.dev/badge/instructions/ashishpatill/tell-proof/agents-md/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/instructions/ashishpatill/tell-proof/agents-md"><img src="https://agentmods.dev/badge/instructions/ashishpatill/tell-proof/agents-md.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 | $0.00999 | $0.00999 |
| Opus 5.5 | $0.00400 | $0.00400 |
| Sonnet 5.5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
tell-proof AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — entry only
Tell Proof is the Cursor / Grok Build plugin for world-class site and app design across many sessions. Agents write code; Tell observes the rendered UI, names genericness tells and drift, takes plain-English art-direction, drafts patches, and proves them in a disposable checkout. Humans approve — tell_apply never writes files.
/studio and /showcase are dogfood and specimens. They are not the product.
Do not load entire docs/. Open only the FEATURE-MAP rows that match this task.
Status: CHANGELOG.md · docs/PROJECT-STATUS.md
Registry: docs/FEATURE-MAP.md · docs/TOOLS-AND-SKILLS.md
Standing rules
- Ship bar: stacked images, motion, artistic, unique. Not one-shot AI generate.
- Park: secondary to DeepHarness honesty — do not pull eng attention here while that is open.
- Local CI only: never wait on or re-run GitHub Actions. Gate on
pnpm test/pnpm typecheck. - Deterministic core (
packages/core): zero LLM. Zod at every boundary (@tell/schema). - Never auto-apply. Tokens only in
apps/web(no raw hex in classNames). - No invented connectors. Skills/MCP/plugins: only what
docs/TOOLS-AND-SKILLS.mdlists as in-repo.
Persona / copy: USER_STORY.md. Engineering contracts: BUILD.md. Checklists: PLAN.md. Visuals: docs/01_DESIGN_SYSTEM.md. Model pins: ORCHESTRATION.md.
Working loop
- Read this file only.
- Match the task to
docs/FEATURE-MAP.mdrow(s). - Open those feature doc(s) + the listed skills / MCP.
- Skip unrelated features.
- When done: prepend
CHANGELOG.md; refresh the matching row indocs/PROJECT-STATUS.md.
Feature → doc
| Feature | Open | When |
|---|---|---|
| Capture → diagnose → prove | docs/features/capture-diagnose-prove.md |
Detectors, Report, seam, proof, fixture |
| MCP plugin (Cursor / Grok) | docs/features/mcp-plugin.md |
tell_* tools, install-info, catalog honesty |
| Design dogfood loop | docs/features/design-dogfood-loop.md |
Tell’s own UI, Studio bar, multi-session craft |
| Training-data / MCP sink | docs/features/training-data-mcp-sink.md |
tell-design-data, SFT/DPO, episode writes |
| Showcase / Tiller | docs/features/showcase-tiller.md |
Specimens, GitHub README stills, Tiller gap |
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 Changed · -111 lines · -1,657 tokens per session e82de839b3a1
- 1mo ago First seen · 177 lines · 2,656 tokens per session scan A 672201fcf50d
tell-proof AGENTS.md is an instructions file published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 999 tokens to every session, about $0.0040 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 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.