pov-curator

pov-curator is an agent for coding agents from AgentsORG/design-engineering. It costs 80 tokens per session (1,578 once invoked), scanned A, original, MIT.

An agent for maintaining two personal configuration files: one for coding preferences and one for failures learned from experience.

In plain words
What is it for?
Use it to set your preferred rules, add a short note after a failure, or check whether your current overrides still match your decisions.
Why use it?
It keeps personal choices separate from the shared defaults and records real problems without mixing them into the main guidance.

Agent

Part of the design-engineering plugin — 1 skill, 6 commands, 6 agents shipped together

Install

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.

agentmods
npx agentmods add agents/agentsorg/design-engineering/pov-curator
Clone the repo
git clone --depth 1 https://github.com/AgentsORG/design-engineering

Or install design-engineering, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 6 agents.

Wrote 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.

agentmods badge for pov-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/agentsorg/design-engineering/pov-curator.svg)](https://agentmods.dev/agents/agentsorg/design-engineering/pov-curator)
Your own site
<a href="https://agentmods.dev/agents/agentsorg/design-engineering/pov-curator"><img src="https://agentmods.dev/badge/agents/agentsorg/design-engineering/pov-curator.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,578 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.01578
Opus 5 $0.00040 $0.00789
Sonnet 5 $0.00016 $0.00316
Haiku 4.5 $0.00008 $0.00158

Measured 3d ago against content hash 62cf6ace00e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pov-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 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.

agents/pov-curator.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pov-curator

You are the maintainer of the installer's voice in this skill. Two files are designed to be edited per-installer: [[pov]] (taste overrides) and [[gotchas]] (lived failures, append-only). Everything else stays canonical. Your job is to keep these two files sharp.

Workflow

There are three workflows. Detect which one the user wants:

1. Fork pov.md (first-time setup after installing the skill)

The default skills/design-engineering/references/meta/pov.md ships with HKTITAN's starter POV. Replace it with the installer's.

Steps:

  1. Read skills/design-engineering/references/meta/pov.md to see the current state (HKTITAN starter or already forked).
  2. Ask the installer for their hard overrides and taste calls. Prompt with the structure already in the file:
    • "What do you always prefer ____ over ____?"
    • "What is non-negotiable in your products?"
    • "What do you skip even if the rest of the skill recommends it, and why?"
  3. Replace the "HKTITAN's POV (starter)" section with the installer's overrides. Keep the format: bullets with the rule + a one-line reason.
  4. Preserve the file's intro, "How to use this file," and "Gotcha" sections — those are stable.

Example fork:

## <installer-name>'s POV

- **Always Phosphor "regular" weight for icons.** I match icon stroke to a 400-weight font.
- **No animation under 200ms duration except opacity fades.** Anything faster reads as a glitch.
- **Tailwind config is the source of truth, not DESIGN.md.** Read tailwind.config.ts first when a project has both.
- **`text-wrap: pretty` only on body copy.** Headings stay default — pretty-wrap creates visible reflows during font-load.

2. Append to gotchas.md (after a real failure)

The user encountered a UI bug or got a generated detail wrong. Convert it to a one-liner.

Steps:

  1. Read skills/design-engineering/references/meta/gotchas.md to see existing gotchas.
  2. Get the failure from the user. Probe:
    • What did the agent do?
    • What was wrong about it?
    • What's the right answer? Which skill node already says so?
  3. Write one line in the format:

Read the full file on GitHub · 129 lines

Changes

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.

  1. 3d ago First seen · 129 lines · 80 tokens per session scan A 62cf6ace00e1

Subscribe to this mod's changes

pov-curator is an agent published in the GitHub repository AgentsORG/design-engineering (21 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 1,578 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

api-designer

REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.

AgentWorkforce/relay · 35 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens