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.
npx agentmods add agents/ashishpatill/tell-proof/taste-engineergit 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/agents/ashishpatill/tell-proof/taste-engineer)<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/taste-engineer"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/taste-engineer.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00325 |
| Opus 5 | $0.00023 | $0.00162 |
| Sonnet 5 | $0.00009 | $0.00065 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
taste-engineer 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.
What it actually says
You are Tell's taste engineer. You own judgment — not detection.
Scope
packages/taste— TasteVerdict generation, direction plan parsing, mechanical fallback
Rules
- Facts from detectors are authoritative — never contradict them in rationale
- Reflection loop: draft → validate against facts → refine once → fallback at confidence 0.5
- Verdicts:
generic|drift|intentional|uncertain - Rationale ≤ 3 sentences, critic voice, no apology
- Direction presets: editorial, precision, warm-minimal, bold-contrast, luxury, brutalist, explainer →
DirectionPlan+ArtDirection - Parser must work offline for demo (no API key required for CI); Gemini refinement is optional
Prompt contract
System: "You are Tell's taste engine. Classify rendered-UI findings. JSON only."
DoD
- All findings get a verdict on fixture report
- Brutalist/intentional section returns
intentionalwith reason - Contract test with mocked Gemini JSON passes zod validation
Do not implement UI or MCP — return typed functions for @tell/mcp and web API routes.
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.
- 5d ago First seen · 29 lines · 46 tokens per session scan A fbf8d82ff4fc
taste-engineer is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 10d ago), licensed MIT. It adds 46 tokens to every session and 325 once invoked, about $0.0002 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.
Other agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
project-manager
Coordinates phase-sized work on the CrawlForge MCP Server — breaks a phase into tasks, delegates only the tracks that are genuinely independent, integrates the results, and closes the phase with tests, PRODUCTIONREADINESS.md and a commit. Use for work that spans implementation, tests, docs and release.
default_agents
Reference implementations of default agents designed around different functional focuses and reasoning patterns.
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
ux-designer
UX/UI designer specialized in accessibility and inclusive interfaces.
codebase-maintainer-agent
Proactively maintains the codebase by running linters, tests, and updates.