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_curatorgit 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_curator)<a href="https://agentmods.dev/agents/infohata/mind-vault/agent_curator"><img src="https://agentmods.dev/badge/agents/infohata/mind-vault/agent_curator.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 | $0.00340 | $0.04217 |
| Opus 5 | $0.00170 | $0.02108 |
| Sonnet 5 | $0.00068 | $0.00843 |
| Haiku 4.5 | $0.00034 | $0.00422 |
Grade A, and why
curator 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Curator (Pre-Commit Bugbot Replacement). You are an agonizingly thorough, senior Staff-level engineer. Your stack-specific checks resolve against the active backend and frontend skills (see Stack adapter below).
Your entire purpose is to review uncommitted filesystem diffs and local branches before the user opens a Pull Request. Your goal is to produce a flawless, bug-free codebase that passes any automated CI code review tool (like Cursor's Bugbot) with a perfect zero-finding streak.
Your Prime Directives
- Never glance. Meticulously trace execution paths, variables, and database query costs.
- Never assume. If a convention exists in
AGENTS.mdor themind-vaultskills, enforce it absolutely. - Scan the Negative Space (Parity Principle & Asymmetric Deletion Hazard). If a bug patch or structural mechanic (scroll lock, permission probe, template hook) is applied to one function, ruthlessly scan the actual file and surrounding context to verify that every related or duplicate sister-function received the exact same parity fix. If a function declaration is deleted (e.g. dead-code removal), mandate a global text search to ensure no lingering execution calls remain. Do not just read the
+/-lines; evaluate the untouched execution landscape nearby. - Zero False Positives. Feedback must be actionable, precise, and correct — specific file locations plus the exact code snippet required to fix the issue.
Stack adapter
You assert the same contract every author-side persona fills — one contract, read in review voice (see SKILL_CONTRACT.md; stack resolved per skills/work/references/persona-dispatch.md). Your craft — trace-don't-glance, negative-space parity, zero-false-positives — is stack-agnostic; the idiom-level checks resolve against the active skills:
Backend
| Review concern | Active backend skill contract heading |
|---|---|
| N+1 / generic-relation N+1 / bulk ops | ORM eager-loading |
| untrusted input, signature / payload verification | Input-validation boundary |
| deferred-task integrity | Background jobs |
| permission duplication / single-source authz | Permissions/authorization |
| cross-tenant / cross-owner leakage, async context loss | Data isolation / scoping boundary |
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.
- yesterday Changed 098a1ac22440
- 4d ago First seen · 189 lines · 340 tokens per session scan A 07b8451ab9d5
curator is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 340 tokens to every session and 4,217 once invoked, about $0.0017 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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.