crux-cockpit

crux-cockpit is a skill for Claude Code, Codex from mehdiforoozandeh/crux. It costs 197 tokens per session (4,630 once invoked), scanned C, original, MIT.

A local, read-only web interface for exploring a crux research vault: a structured collection of questions, evidence, hypotheses, reports, and figures. It displays the vault as a searchable tree and lets you inspect linked research details.

In plain words
What is it for?
Use it to start, verify, and manage the local viewer; browse the research tree, search and focus on questions, review queued items, inspect node details, and open linked reports and figures.
Why use it?
It makes a research vault easier to navigate and review than reading its files directly, without changing the underlying research.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to start, verify, and manage the local viewer; browse the research tree, search and focus on questions, review queued items, inspect node details, and open linked reports and figures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mehdiforoozandeh/crux/crux-cockpit
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.

Any agent
npx skills add mehdiforoozandeh/crux --skill crux-cockpit
Clone the repo
git clone --depth 1 https://github.com/mehdiforoozandeh/crux

Made for: Claude Code, Codex.

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 crux-cockpit

README.md
[![agentmods](https://agentmods.dev/badge/skills/mehdiforoozandeh/crux/crux-cockpit/github.svg)](https://agentmods.dev/skills/mehdiforoozandeh/crux/crux-cockpit)
Your own site
<a href="https://agentmods.dev/skills/mehdiforoozandeh/crux/crux-cockpit"><img src="https://agentmods.dev/badge/skills/mehdiforoozandeh/crux/crux-cockpit/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 crux-cockpit

Your own site · 80×15
<a href="https://agentmods.dev/skills/mehdiforoozandeh/crux/crux-cockpit"><img src="https://agentmods.dev/badge/skills/mehdiforoozandeh/crux/crux-cockpit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,630 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00197 $0.04630
Opus 5 $0.00098 $0.02315
Sonnet 5 $0.00039 $0.00926
Haiku 4.5 $0.00020 $0.00463

Measured 12d ago against content hash ab41eb762337, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

crux-cockpit scanned grade C with 2 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 12d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsS "$URL/snapshot.json" | python3 -c \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

and `/snapshot.json` must have answered 200 from *your* curl. A URL you haven't verified
skills/crux-cockpit/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

crux-cockpit — launch the crux GUI, beginning to finish

The cockpit is crux's read-only browser GUI: crux serve boots a stdlib HTTP server on 127.0.0.1, serves the webui/ frontend, and exposes the vault as /snapshot.json (status-colored tree — pan / zoom / collapse / search / re-orient / focus one question — plus the review queue, node detail with rendered markdown, and a hypothesis's linked report and figures; live-refreshing, zero writes). Either panel can go full-screen ([ / ], Esc restores). The engine does the serving; you (the agent) do the operating: find the vault, launch clean, verify, hand over one URL, and manage the server's lifecycle. The user should never have to touch a terminal on the machine you run on — the one thing you can't do for them is start a local ssh -L tunnel (plain-SSH contexts only; see Local vs remote).

The engine rides in the crux skill: ENGINE = <crux skill>/scaffold/crux.py — the crux skill is this skill's sibling directory in your skills dir (in a repo clone, skills/crux). If that engine file is missing, the crux skill isn't installed: install it first (npx skills add mehdiforoozandeh/crux --all, or the repo's ./install.sh) before continuing.

Ground rules (load-bearing)

  • Never report an unverified URL. Before telling the user the cockpit is up, both / and /snapshot.json must have answered 200 from your curl. A URL you haven't verified does not leave your mouth.
  • URL only — never pop a browser. Always launch with --no-open and deliver the URL as a clickable link. The user opens it when ready. One carve-out: in VS Code Remote-SSH the sanctioned way to create the port forward is an open call (code --openExternal — see the ladder below); there, opening the user's browser is the mechanism, not a discourtesy.
  • Always fresh, per vault. A launch first kills any cockpit already serving that vault — and never touches cockpits serving other vaults (several can coexist on different ports).
  • The cockpit is read-only. No route writes; every mutation stays in the agent/CLI. Never present it as an editor.
  • Surface engine-drift warnings. If the launch log warns that the vault was stamped by a different engine version, relay that warning to the user verbatim.

Read the full file on GitHub · 291 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. 12d ago First seen · 291 lines · 197 tokens per session scan C ab41eb762337

Subscribe to this mod's changes

crux-cockpit is a skill published in the GitHub repository mehdiforoozandeh/crux (6 stars, last pushed 6d ago), licensed MIT. It adds 197 tokens to every session and 4,630 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ab-testing

Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go significant. NOT recurring metric tracking (that is analytics), NOT north-star/KPI trees (that is kpi-framework), NOT projecting metrics…

ericrisco/rsc-harness · 79 tokens

product-principles

Defines 4 Risks confidence thresholds, OST hierarchy levels, Knowledge Pyramid tiers, and state design requirements. Use when evaluating user stories, setting confidence scores, referencing OST levels, scoping MVP, or determining validation sufficiency.

shinpr/claude-code-discover · 49 tokens

recipe-define

Orchestrate PRD creation from validated hypotheses — standard PRD output with 4 Risks confidence and hypothesis traceability.

shinpr/claude-code-discover · 27 tokens

recipe-validate

Orchestrate hypothesis validation through type-appropriate methods — prototypes, code analysis, market research, and expert review.

shinpr/claude-code-discover · 26 tokens

hypothesis-discipline

Manages hypothesis lifecycle, enforces validation criteria, time budgets, and confidence scoring rules. Use when creating hypotheses, updating confidence scores, setting validation criteria, handling timeouts, or recording validation results.

shinpr/claude-code-discover · 45 tokens

blueprint-standards

Defines structural design artifact formats — information architecture, user flows, content model, brand direction, and AI interaction model. Use when creating or reviewing structural design documents that precede prototype generation.

shinpr/claude-code-discover · 43 tokens