kickoff

kickoff is a command for Claude Code from VelimirMueller/vlm-code-context-mcp. It costs 0 tokens per session (3,226 once invoked), scanned A, original, MIT.

An interactive project kickoff command that guides a team from product vision through planning, implementation, and a sprint review.

In plain words
What is it for?
Use it to run discovery, define larger work areas and tickets, plan a sprint, implement selected work, and hold a retrospective.
Why use it?
It gives a project a structured path from an idea to planned and reviewed work, while preserving context between stages.

Command for Claude Code

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 commands/velimirmueller/vlm-code-context-mcp/kickoff
Clone the repo
git clone --depth 1 https://github.com/VelimirMueller/vlm-code-context-mcp

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 kickoff

README.md
[![agentmods](https://agentmods.dev/badge/commands/velimirmueller/vlm-code-context-mcp/kickoff.svg)](https://agentmods.dev/commands/velimirmueller/vlm-code-context-mcp/kickoff)
Your own site
<a href="https://agentmods.dev/commands/velimirmueller/vlm-code-context-mcp/kickoff"><img src="https://agentmods.dev/badge/commands/velimirmueller/vlm-code-context-mcp/kickoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,226 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 $0.00000 $0.03226
Opus 5 $0.00000 $0.01613
Sonnet 5 $0.00000 $0.00645
Haiku 4.5 $0.00000 $0.00323

Measured 3d ago against content hash 01e1f2061dda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kickoff 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.

.claude/commands/kickoff.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Project Kickoff — Interactive Guided Sprint Lifecycle

Run the complete scrum lifecycle from product vision through sprint rest. Use native question UI for every structured choice, render server-built cards verbatim, enforce all QA gates and the planning gate.

Step 0 — Load Context (2 calls)

index_directory({ freshness_check: true })   # skip if <5 min old
get_resume_state()                           # single-call resume detection

That's it. get_resume_state() returns vision, sprints, discoveries, milestones, epics, agents, and next_phase in ~150 tokens.

Phase context — load with load_phase_context() when entering each phase

Phase Call
Phase 2 load_phase_context({ phase: "discovery" })
Phase 4 load_phase_context({ phase: "epics" })
Phase 5+5b load_phase_context({ phase: "tickets" }) — includes the planning-gate blocks
Phase 7 load_phase_context({ phase: "implementation", sprint_id, ticket_id })
Phase 8 load_phase_context({ phase: "retro", sprint_id })

Display summary

Render the resume state as a phase banner + yaml data card:

◈ Context Loaded

vision:      set                  # from get_resume_state()
sprints:     21 completed · none active
discoveries: 9 active
milestone:   "#21 Process 2.0"    # [active] 40%
skill_sets:  fe ✓ · la ✗ · wf ✗   # "(defaults — not configured yet)" → Phase 1b will ask
next_phase:  tickets

Output Contract — Design Language 2.0

  1. Server cards are verbatim. Tools called with format: "card" (update_ticket, advance_sprint, start_sprint, get_sprint_playbook, get_burndown) return pre-rendered card lines. Print them unchanged inside a ```diff fence. Never redraw, restyle, re-align, or wrap them.
  2. Phase banners are a ## ◈ <Phase Title> markdown heading followed by a ```yaml data card (keys lowercase, aligned values, # comments for context). Never hand-draw ASCII boxes.
  3. Use format: "card" on every status-changing call during ceremonies — each card includes compact state, so skip follow-up get_ticket/get_sprint calls.

Read the full file on GitHub · 262 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 · 262 lines · 0 tokens per session scan A 01e1f2061dda

Subscribe to this mod's changes

kickoff is a command published in the GitHub repository VelimirMueller/vlm-code-context-mcp (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,226 tokens. 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.