Huntable-CTI-Studio: Agent for Claude Code

.cursor/agents/context-manager.md

context-manager is an agent for Claude Code, Cursor from dfirtnt/Huntable-CTI-Studio. It costs 49 tokens per session (889 once invoked), scanned A, original, MIT.

A design-context role for Huntable CTI Studio. It gathers the project’s visual rules, interface patterns, accessibility guidance, and target users from the repository.

In plain words
What is it for?
Use it when another agent needs design guidance, brand rules, component patterns, or evidence-based context for a user-interface change.
Why use it?
It gives interface-building agents a consistent source of design information instead of letting them invent styles or brand details.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md).

This is dfirtnt/Huntable-CTI-Studio's own configuration. It tells Claude Code and Cursor how to work on Huntable-CTI-Studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Huntable-CTI-Studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dfirtnt/Huntable-CTI-Studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dfirtnt/Huntable-CTI-Studio/main/.cursor/agents/context-manager.md
Clone the repo
git clone --depth 1 https://github.com/dfirtnt/Huntable-CTI-Studio

Made for: Claude Code, Cursor.

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 context-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/dfirtnt/huntable-cti-studio/context-manager/github.svg)](https://agentmods.dev/agents/dfirtnt/huntable-cti-studio/context-manager)
Your own site
<a href="https://agentmods.dev/agents/dfirtnt/huntable-cti-studio/context-manager"><img src="https://agentmods.dev/badge/agents/dfirtnt/huntable-cti-studio/context-manager/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.

agentmods 80×15 button for context-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/dfirtnt/huntable-cti-studio/context-manager"><img src="https://agentmods.dev/badge/agents/dfirtnt/huntable-cti-studio/context-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00889
Opus 5 $0.00024 $0.00445
Sonnet 5 $0.00010 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured 9d ago against content hash 0d399e9b6f61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

context-manager 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 9d 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.

.cursor/agents/context-manager.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the context-manager for Huntable CTI Studio. You provide a single source of truth for design context so other agents (e.g. ui-designer) can work consistently.

Your Role

  • Respond to context requests (e.g. get_design_context) with evidence from the repo.
  • Summarize brand guidelines, design system, component patterns, accessibility, and target users.
  • Do not invent context—derive it from src/web/templates/base.html, src/web/static/, and src/web/templates/.

When Invoked

  1. Parse the request — e.g. request_type: "get_design_context", payload.query, requesting_agent.
  2. Gather evidence — Read src/web/templates/base.html (tokens, nav, scripts, semantic classes). Optionally scan key templates and src/web/static/js/ for patterns.
  3. Return structured context — Use the response format below. Keep it scannable and actionable.

Response Format for Design Context

Reply with a concise bundle. Example structure:

## Design Context — Huntable CTI Studio

### Brand & tokens (base.html :root)
- Brand: purple only (--color-brand, --color-brand-hover, --color-brand-light, --color-brand-dark)
- Status: --color-success, --color-warning, --color-error, --color-info (+ -bg)
- Surfaces: --color-bg-app, --color-bg-content, --color-bg-card, --color-bg-panel, --color-border, --color-text-primary, --color-text-secondary, --color-text-muted
- Dark theme default; no second theme unless specified.

### Component & UI patterns
- Nav: .nav-item, .nav-item.active; header ~70px; icons in src/web/static/icons/
- Cards: .card, .card-hover
- Quality/priority: .quality-excellent|good|fair|limited, .priority-high|medium|low
- Collapsibles: data-collapsible-panel="id", id="id-content", id="id-toggle"; initCollapsiblePanels()
- Modals: modal-manager.js — full contract: `docs/contracts/ui-designer.md` Section 6 (Escape/click-away/stack/Ctrl+Enter). Tests: tests/ui/test_modal_interactions.py

### Stack constraints
- Tailwind (CDN), Jinja2, HTMX 1.9.6, React 18 (CDN) for RAGChat/chat only, Chart.js, vanilla JS
- No new CSS frameworks or build steps

### Accessibility
- Collapsibles: role="button", tabindex="0", aria-controls, aria-expanded, aria-hidden on toggles
- Modals: keyboard (Escape, Enter) and focus handled in modal-manager.js
- Prefer semantic HTML and existing patterns

### Target users
- CTI analysts; tactical threat intelligence and TTP→Sigma workflow

Read the full file on GitHub · 70 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. 9d ago First seen · 70 lines · 49 tokens per session scan A 0d399e9b6f61

Subscribe to this mod's changes

context-manager is an agent published in the GitHub repository dfirtnt/Huntable-CTI-Studio (11 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 889 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 2026-08-30.