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.
npx skills add Maximepodgorski/agent-skills --skill kickoffgit clone --depth 1 https://github.com/Maximepodgorski/agent-skillsWrote 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.
[](https://agentmods.dev/skills/maximepodgorski/agent-skills/kickoff)<a href="https://agentmods.dev/skills/maximepodgorski/agent-skills/kickoff"><img src="https://agentmods.dev/badge/skills/maximepodgorski/agent-skills/kickoff/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.
<a href="https://agentmods.dev/skills/maximepodgorski/agent-skills/kickoff"><img src="https://agentmods.dev/badge/skills/maximepodgorski/agent-skills/kickoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.02665 |
| Opus 5 | $0.00057 | $0.01333 |
| Sonnet 5 | $0.00023 | $0.00533 |
| Haiku 4.5 | $0.00012 | $0.00266 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kickoff
Project context kickoff. Conversational interview that builds structured docs for AI agents.
Agent Capabilities
| Capability | Used For | Required | Fallback |
|---|---|---|---|
| File read/write | .context/ docs, CLAUDE.md |
Yes | -- |
| Code search (grep/glob) | Bootstrap scan, drift detection | Recommended | User describes project manually |
| User interaction | Conversational interview, confirmations | Yes | -- |
| Task/subagent | analyze action (parallel reviewers) |
Recommended | Single-agent analysis |
| Shell/command execution | Git log, package.json read | Recommended | User provides info manually |
Fallback rule: If codebase access is limited, the skill works from conversation alone. Warn the user and proceed.
Actions
| Action | Input | Output | Reference |
|---|---|---|---|
init |
(none) or project path | .context/ folder with axis docs |
init.md |
update {axis} |
Axis name (product, engineering, etc.) | Updated axis docs | update.md |
todo |
(none) — reads .context/TODO.md |
Updated context docs + trimmed TODO | todo.md |
analyze |
(none) — reads existing .context/ |
Analysis report with findings | analyze.md |
review |
(none) — reads .context/ + codebase |
Drift report | review.md |
generate |
(none) — reads .context/ |
CLAUDE.md (or agent-specific config) | generate.md |
Flow
First time (kickoff):
init → todo (answer open questions) → generate
With existing codebase:
init (bootstraps from artifacts) → todo → generate
Maintenance:
update {axis} → generate
Enrich context:
todo → generate
Health check:
review → update (if drift detected) → generate
Strategic challenge:
analyze → update (if insights) → generate
Quick regeneration:
generate (reads existing .context/)
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 9.5 KB
- references/actions/analyze.md 5.3 KB
- references/actions/generate.md 5.3 KB
- references/actions/init.md 8.1 KB
- references/actions/review.md 7.0 KB
- references/actions/todo.md 3.4 KB
- references/actions/update.md 4.1 KB
- references/principles/interview.md 7.3 KB
- references/templates/axes/business.md 1.5 KB
- references/templates/axes/decisions.md 1.5 KB
- references/templates/axes/design.md 1.7 KB
- references/templates/axes/engineering.md 7.6 KB
- references/templates/axes/marketing.md 1.1 KB
- references/templates/axes/product.md 7.6 KB
- references/templates/axes/team.md 1.3 KB
- references/templates/claude-md.md 4.1 KB
- references/templates/context-file.md 15 KB
- references/templates/decision-record.md 1.7 KB
- references/templates/meta.md 2.1 KB
- references/templates/outputs/analyze-output.md 1.0 KB
- references/templates/outputs/generate-output.md 822 B
- references/templates/outputs/init-output.md 1.1 KB
- references/templates/outputs/review-output.md 1.2 KB
- references/templates/outputs/todo-output.md 635 B
- references/templates/outputs/update-output.md 423 B
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.
- 10d ago First seen · 254 lines · 115 tokens per session scan A 627dc093cc7b
kickoff is a skill published in the GitHub repository Maximepodgorski/agent-skills (21 stars, last pushed 4mo ago), licensed MIT. It adds 115 tokens to every session and 2,665 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…