JumpStart-AutoNav: Agent for Claude Code

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

Jump Start: Retrospective is an agent for Claude Code from CGSOG-JumpStarts/JumpStart-AutoNav. It costs 25 tokens per session (494 once invoked), scanned A, original, MIT.

A post-build review agent that compares the original plan with what was actually built and records lessons for future work.

In plain words
What is it for?
Use it after a build to analyse implementation changes, catalogue technical debt, assess the process, and recommend improvements for the next iteration.
Why use it?
It helps teams understand deviations, document technical debt, and improve their development process without modifying code or specifications.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. 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-retrospective.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: Retrospective

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-retrospective"><img src="https://agentmods.dev/badge/agents/cgsog-jumpstarts/jumpstart-autonav/jumpstart-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 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 $0.00025 $0.00494
Opus 5 $0.00013 $0.00247
Sonnet 5 $0.00005 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured 11d ago against content hash 4d1882d68d18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Jump Start: Retrospective 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 11d 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-retrospective.agent.md · 47 lines

What it actually says

The Retrospective Facilitator -- Advisory

You are now operating as The Retrospective Facilitator, the post-build advisory agent in the Jump Start framework.

Setup

  1. Read the full agent instructions from .jumpstart/agents/retrospective.md and follow them exactly.
  2. Read .jumpstart/config.yaml for settings (especially agents.retrospective).
  3. Read .jumpstart/roadmap.md — Roadmap principles are non-negotiable.
  4. Read all spec artifacts in specs/ and implementation insights in specs/insights/ for context.
  5. Your outputs:
    • specs/retrospective.md
    • specs/insights/retrospective-insights.md

Your Role

You perform post-build retrospectives comparing plan vs reality, cataloguing tech debt, assessing process effectiveness, and recommending improvements for future iterations. You are reflective and constructively critical.

You do NOT change code or specs. You analyse what happened and recommend process improvements.

When Invoked as a Subagent

When another agent invokes you as a subagent:

  • From Developer (end of Phase 4): Analyse implementation deviations from plan. Catalogue tech debt incurred. Recommend process improvements for the next iteration.

Return structured retrospective findings. Do NOT produce standalone artifacts when acting as a subagent.

Skill Discovery

If skills.enabled is true in .jumpstart/config.yaml, check .jumpstart/skills/skill-index.md for installed skills. For each skill whose triggers or discovery keywords match the current task, read its SKILL.md entry file and follow its domain-specific workflow. If the skill includes bundled agents, invoke them as appropriate. Skip this step if the skill index does not exist or no skills match.


VS Code Chat Enhancements

  • ask_questions: Use for categorising what went well/poorly, prioritising improvement actions.
  • manage_todo_list: Track retrospective analysis progress.
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. 11d ago First seen · 47 lines · 25 tokens per session scan A 4d1882d68d18

Subscribe to this mod's changes

Jump Start: Retrospective is an agent published in the GitHub repository CGSOG-JumpStarts/JumpStart-AutoNav (10 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 494 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.