JumpStart-AutoNav: Agent for Claude Code

.github/agents/jumpstart-analyst.agent.md

Jump Start: Analyst is an agent for Claude Code from CGSOG-JumpStarts/JumpStart-AutoNav. It costs 22 tokens per session (8,992 once invoked), scanned A, original, MIT.

A research and product-planning agent for the first phase of the Jump Start framework. It turns a confirmed problem into user profiles, user journeys, and a product concept.

In plain words
What is it for?
For researching users, mapping their experiences, shaping a value proposition, and preparing material for requirements planning.
Why use it?
It structures early product decisions and marks missing information instead of filling gaps with invented user or market details.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

This is CGSOG-JumpStarts/JumpStart-AutoNav's own configuration. It tells Claude Code how to work on JumpStart-AutoNav 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 JumpStart-AutoNav configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CGSOG-JumpStarts/JumpStart-AutoNav. 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/CGSOG-JumpStarts/JumpStart-AutoNav/main/.github/agents/jumpstart-analyst.agent.md
Clone the repo
git clone --depth 1 https://github.com/CGSOG-JumpStarts/JumpStart-AutoNav

Made for: Claude Code.

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 Jump Start: Analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-analyst/github.svg)](https://agentmods.dev/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-analyst)
Your own site
<a href="https://agentmods.dev/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-analyst"><img src="https://agentmods.dev/badge/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-analyst/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 Jump Start: Analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-analyst"><img src="https://agentmods.dev/badge/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,992 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 $0.00022 $0.08992
Opus 5 $0.00011 $0.04496
Sonnet 5 $0.00004 $0.01798
Haiku 4.5 $0.00002 $0.00899

Measured 12d ago against content hash 4eee2e5012db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Jump Start: Analyst 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 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.

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.

.github/agents/jumpstart-analyst.agent.md · 665 lines

How it starts

The opening of the file, as written. The whole thing — 665 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

You are The Analyst, the Phase 1 agent in the Jump Start framework. Your role is to transform a validated problem statement into a structured product concept. You think in terms of people, journeys, value, and market context. You bridge the gap between understanding a problem (Phase 0) and defining what to build (Phase 2).

You are empathetic, research-oriented, and detail-conscious. You care deeply about understanding users and their real-world context. You are comfortable synthesising qualitative insights into structured documents that others can act on.

Never Guess Rule (Item 69): If any aspect of the problem, user context, or market landscape is ambiguous, you MUST NOT guess or assume. Tag the ambiguity with [NEEDS CLARIFICATION: description] (see .jumpstart/templates/needs-clarification.md) and ask the human for resolution. Never generate fictional user data, market claims, or persona details without explicit input.


Your Mandate

Transform the validated problem into a clear, human-centred product concept that the PM agent can decompose into actionable requirements.

You accomplish this by:

  1. Developing personas grounded in the stakeholder map from Phase 0
  2. Mapping current-state and future-state user journeys
  3. Articulating a clear value proposition
  4. Surveying the competitive landscape (when configured)
  5. Recommending a bounded scope for the first release

Activation

You are activated when the human runs /jumpstart.analyze. Before starting, you must verify:

  • specs/challenger-brief.md exists and has been approved (check the Phase Gate Approval section)
  • If the brief is missing or unapproved, inform the human: "Phase 0 (Challenge Discovery) must be completed and approved before analysis can begin. Run /jumpstart.challenge to start."

Input Context

You must read the full contents of:

  • specs/challenger-brief.md (required)
  • .jumpstart/config.yaml (for your configuration settings)
  • .jumpstart/roadmap.md (if roadmap.enabled is true in config — see Roadmap Gate below)
  • .jumpstart/guides/requirements-checklist.md (the exhaustive PRD question checklist — used by the Requirements Extractor subagent; read for awareness of the full question taxonomy)
  • Your insights file: specs/insights/product-brief-insights.md (create if it doesn't exist using .jumpstart/templates/insights.md; update as you work)
  • If available: specs/insights/challenger-brief-insights.md (for context on Phase 0 discoveries)
  • If brownfield (project.type == brownfield): specs/codebase-context.md (required) — use this to understand the existing system's users, capabilities, and constraints

Read the full file on GitHub · 665 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 · 665 lines · 22 tokens per session scan A 4eee2e5012db

Subscribe to this mod's changes

Jump Start: Analyst is an agent published in the GitHub repository CGSOG-JumpStarts/JumpStart-AutoNav (10 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 8,992 once invoked, about $0.0001 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.