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.
git 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/rules/ashishpatill/tell-proof/tell-mission)<a href="https://agentmods.dev/rules/ashishpatill/tell-proof/tell-mission"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-mission/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/rules/ashishpatill/tell-proof/tell-mission"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-mission.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 | $0.00367 | $0.00367 |
| Opus 5.5 | $0.00147 | $0.00147 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
tell-mission 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 2mo 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 — always apply
Read USER_STORY.md: we build for Ashish (solo founder, AI-built UI looks generic, demo tomorrow).
Golden rules
- Product = capture -> diagnose -> art-direct -> reconcile; the report serves the loop, not a dashboard.
- Deterministic through capture, fingerprint, detection, and baseline reconciliation; LLM only in taste, voice refinement, or enhanced diff paths.
- Never auto-apply fixes. MCP/web returns patches; a human or Cursor agent reviews and applies.
- Zod schemas at every package/API/MCP boundary via
@tell/schema. - Tell's own UI must dogfood the detector rules: tokens, state coverage, contrast, no generic SaaS tells.
- Preserve demo reliability: live path first, committed fixture/report fallback always works.
Model routing (see ORCHESTRATION.md)
- Composer 2.5 — orchestrate, UI, MCP, fixtures
- Opus 4.8 — schema, detectors, taste engine
- GPT 5.5 — user copy, demo narrative
Delegate to subagents
.cursor/agents/ — 11 role-specific agents. Use proactively by feature area.
Project skills
.cursor/skills/ — feature workflows. Invoke with @skill-name or let Cursor auto-attach.
Website builds auto-trigger research: always-applied rule tell-domain-research + engine
routeSkills prepends website-domain-research (and sport-matchday-web when sport). Agents
must execute LoadPrior → gap → walkthrough if needed → IA → training emit before pixels.
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.
- 2mo ago First seen · 33 lines · 367 tokens per session scan A 69c5fb79e8e0
tell-mission is a cursor rule published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 1mo ago), licensed MIT. It adds 367 tokens to every session, about $0.0015 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.
tell-mission compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tell-missionashishpatill/tell-proof | Cursor rule | 2 | 1mo ago | MIT | A | 367 | Cursor |
| orchestrateNITISH-R-G/hackerrank-orchestrate-skills | Cursor rule | 9 | 21d ago | MIT | A | 67 | Cursor |
| cursormrwogu/promptscript | Cursor rule | 344 | 4d ago | MIT | A | 53 | Cursor |
| archcore-filesarchcore-ai/plugin | Cursor rule | 58 | 1mo ago | Apache-2.0 | A | 0 | Cursor |
| orchestrator-mainmadebyaris/agent-orchestration | Cursor rule | 21 | 7mo ago | MIT | A | 11 | Cursor |
| leanousid/lean | Cursor rule | 4 | 3mo ago | MIT | A | 221 | Cursor |
| secure-dev-rustmatank001/cursor-security-rules | Cursor rule | 383 | 1y ago | MIT | A | 0 | Cursor |