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-plumbing-reference)<a href="https://agentmods.dev/rules/ashishpatill/tell-proof/tell-plumbing-reference"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-plumbing-reference/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-plumbing-reference"><img src="https://agentmods.dev/badge/rules/ashishpatill/tell-proof/tell-plumbing-reference.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 | $0.00453 | $0.00453 |
| Opus 5.5 | $0.00181 | $0.00181 |
| Sonnet 5.5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
tell-plumbing-reference 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
Plumbing & platform reference (project memory)
Tell keeps an anonymised study of a peer local-first design daemon for patterns only (MCP install strategies, CLI shipping, skill staging, route-class auth, design-task flow shapes). Use it when building agent/platform features.
Where the plans live (committed)
| Doc | Scope |
|---|---|
docs/11_AGENT_PLATFORM_INTEGRATION_PLAN.md |
MCP, one-click/deeplink install, CLI, skills packaging, multi-agent hosts |
docs/12_AUTH_SECURITY_BOUNDARIES_PLAN.md |
Capture tokens, origins, run-scoped capabilities, pairing — not product login |
docs/13_DESIGN_CAPABILITY_FLOWS_PLAN.md |
Common/complex design tasks mapped onto Ashish's loop |
Where the peer identity lives (never commit)
research/plumbing-reference.local.json— clone URL, local checkout path, study notes- Same anonymity rule as
research/corpus.local.json: no third-party product names or URLs in committed code, docs, comments, or commit messages
How to use the reference
- If the local JSON exists, clone/update to the path it names (default
/tmp/learn-plumbing/reference). - Study patterns; implement Tell-shaped equivalents under
packages/*,apps/web,@tell/schema. - For template layout plumbing only (sticky, stacking, focus, landmarks),
follow
tell-template-craftPhase A → encode floors inbasics-checklist.ts. - For craft/aesthetics, use
design-research-loop+docs/10_DESIGN_EVIDENCE.mdonly — never peer theme packs.
Non-negotiables when adapting
- Deterministic core; never auto-apply; zod at boundaries; offline fixture fallback
- Do not copy peer source into this repo
- Do not mention the peer’s name in anything that gets committed
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 · 42 lines · 453 tokens per session scan A 0554265ef8a7
tell-plumbing-reference is a cursor rule published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 453 tokens to every session, about $0.0018 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 cursor rules, from other repositories
archcore-context
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
demo-consume-context
Worked example that discovers, loads, and tags a context package per CONSUMING-CONTEXT-PACKAGE.md, then writes a reverse-index addendum — proves the produce/consume/tag loop end-to-end. Do NOT use for real feature work.
agentmemory
AgentMemory MCP server rules — use addmemory before answering any question that introduces a project-specific convention, dependency, or constraint.
avos-agent-workflow
Avos memory workflow for AI coding agents. Guides codebase search and history lookup.
knowledge-management-rule
Comprehensive knowledge management system for capturing, organizing, and applying project knowledge.
004_auto_context
Rules for requesting relevant memory context based on file types, locations, and current activity.