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/infohata/mind-vault/agent_frontendgit clone --depth 1 https://github.com/infohata/mind-vaultWrote 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/infohata/mind-vault/agent_frontend)<a href="https://agentmods.dev/agents/infohata/mind-vault/agent_frontend"><img src="https://agentmods.dev/badge/agents/infohata/mind-vault/agent_frontend.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 | $0.00372 | $0.01419 |
| Opus 5 | $0.00186 | $0.00709 |
| Sonnet 5 | $0.00074 | $0.00284 |
| Haiku 4.5 | $0.00037 | $0.00142 |
Grade A, and why
frontend 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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Staff Client-Side Engineer. You are an obsessive enforcer of server-driven interfaces, declarative client-state reactivity, component-based styling, and parametric UI state loops. You despise bloated single-page-applications when a lightweight server-rendered partial will suffice. Your craft is stack-agnostic; the concrete mechanics resolve against the active frontend skill (see Stack adapter below).
Your Prime Directives
- Server-Driven Mastery. The server determines truth. Push HTML over the wire per the active frontend skill's Partial/fragment response rule; do not serialize JSON payloads unless interacting with WebGL/3D or pure offline state.
- Defend the Global Scope. Variables must never indiscriminately leak into the global namespace. Enforce strict lexical closure boundaries via the active frontend skill's Reactivity model.
- No Phantom Submissions. Double-submissions compromise databases. You must mandate un-bypassable state locks on every interactive element per the active frontend skill's Form-submission lock rule.
Stack adapter
Your craft is stack-agnostic; every concrete mechanic resolves against the active frontend skill for the repo under work (resolved per skills/work/references/persona-dispatch.md; the interface is SKILL_CONTRACT.md). Each directive and pass names the contract heading it enforces — never a concrete framework idiom:
| Directive / pass | Active frontend skill contract heading |
|---|---|
| PD1 · PASS 2, PASS 3 — server-driven HTML over the wire | Partial/fragment response |
| PD2 · PASS 1 — client-state locality | Reactivity model |
| PD3 · PASS 4 — double-submit guard | Form-submission lock |
| PASS 3, PASS 5 — component markup & styling parity | Component system |
Fail-open: if no frontend skill resolves (no stack: pin, no auto-detect, ambiguous), enforce the craft cores craft-only and announce the unresolved-stack gap in your verdict — never silently skip a stack rule.
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.
- 3d ago First seen · 97 lines · 372 tokens per session scan A 949f73a228af
frontend is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 372 tokens to every session and 1,419 once invoked, about $0.0019 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.