tell-docs-authority

tell-docs-authority is a cursor rule for Cursor from ashishpatill/tell-proof. It costs 632 tokens per session, scanned A, original, MIT.

A set of project rules that tells an agent which documents define the product, design, engineering, planning, and compliance requirements. It establishes the order and authority to use when those documents overlap.

In plain words
What is it for?
Use it when planning or implementing changes in a project whose requirements are spread across AGENTS.md, USER_STORY.md, BUILD.md, PLAN.md, and related documentation.
Why use it?
It prevents the agent from treating conflicting project documents as equally authoritative. It also points work toward the user story, design system, build rules, and current plan.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add rules/ashishpatill/tell-proof/tell-docs-authority
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Cursor.

Wrote 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.

agentmods badge for tell-docs-authority

README.md
[![agentmods](https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-docs-authority.svg)](https://agentmods.dev/rules/ashishpatill/tell-proof/tell-docs-authority)
Your own site
<a href="https://agentmods.dev/rules/ashishpatill/tell-proof/tell-docs-authority"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-docs-authority.svg" alt="Measured on agentmods" height="20"></a>
Per session 632 This file is loaded in full into every session.
When invoked 632 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00632 $0.00632
Opus 5 $0.00316 $0.00316
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 5d ago against content hash c0dcd143f71c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tell-docs-authority 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 5d 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.

.cursor/rules/tell-docs-authority.mdc · 29 lines

What it actually says

Docs authority

  • Start with AGENTS.md and USER_STORY.md: Ashish's journey is the north star.
  • Visual and interaction contract: docs/01_DESIGN_SYSTEM.md.
  • Engineering rules, stack, milestones, and cut line: BUILD.md.
  • Remaining work / goal+loop prompts: PLAN.md (consolidated). docs/02_* is an archive stub.
  • Screen/design prompt details: docs/03_CLAUDE_DESIGN_BRIEF.md.
  • Vision, scope, demo script, and compliance: docs/04_CLAUDE_PROJECT.md.
  • Genericness definitions and detector methodology: docs/05_GENERICNESS_METHODOLOGY.md.
  • Illustration-first educational / interactive visualization plan: docs/07_VISUALIZATION_PLAN.md (separate from PLAN.md checklists). Do not name external authors, sites, or projects when describing this style.
  • AI design methods + style-addition playbook: docs/08_AI_DESIGN_METHODS.md (packaged judgment / build by piece / reference board). Principle-only — no third-party author, site, skill-marketplace, or tool names.
  • Premium content-custom design skills: docs/09_PREMIUM_DESIGN_SKILLS.md + packages/design-skills. Use aesthetic lean codes (minimal-clean, conversion-sharp, system-crafted, refined-story) — not external person/brand names in runtime keywords.
  • Agent/platform integration (MCP install, CLI, skills shipping): docs/11_AGENT_PLATFORM_INTEGRATION_PLAN.md.
  • Auth/security envelopes (not product login): docs/12_AUTH_SECURITY_BOUNDARIES_PLAN.md.
  • Design capability flows (common + complex tasks): docs/13_DESIGN_CAPABILITY_FLOWS_PLAN.md.
  • Design training-data curation research (no collector in Tell; use separate tell-design-data repo): docs/14_DESIGN_TRAINING_DATA_CURATION_PLAN.md.
  • Design training-data literature survey (cited papers/datasets): research/DESIGN_LLM_TRAINING_DATA_SURVEY.md.
  • Sport matchday vernacular (research before build): research/SPORT_SITE_VERNACULAR.md + skills sport-site-research / sport-vernacular-craft / website-domain-research.
  • Motion/animation capability plan (template + agency ladder): docs/15_MOTION_ANIMATION_PLAN.md.
  • Motion/animation experts + 2026 stacks survey (named; research-only): research/MOTION_ANIMATION_SURVEY.md.
  • Peer plumbing identity is gitignored (research/plumbing-reference.local.json); never name that peer in commits.
  • If BUILD.md and archived docs/02_* drift, treat root BUILD.md as the working source.
  • Do not read .env or .env.local for routine work; use .env.example and README docs for configuration.
Changes

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.

  1. 5d ago First seen · 29 lines · 632 tokens per session scan A c0dcd143f71c

Subscribe to this mod's changes

tell-docs-authority is a cursor rule published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 10d ago), licensed MIT. It adds 632 tokens to every session, about $0.0032 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.