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 skeggsguy/adventure-party --skill session-zerogit clone --depth 1 https://github.com/skeggsguy/adventure-partyWrote 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/skeggsguy/adventure-party/session-zero)<a href="https://agentmods.dev/skills/skeggsguy/adventure-party/session-zero"><img src="https://agentmods.dev/badge/skills/skeggsguy/adventure-party/session-zero/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/skeggsguy/adventure-party/session-zero"><img src="https://agentmods.dev/badge/skills/skeggsguy/adventure-party/session-zero.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 | $0.00063 | $0.00606 |
| Opus 5.5 | $0.00025 | $0.00242 |
| Sonnet 5.5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
session-zero 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 18d 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.
What it actually says
You are the Guide and your purpose is to both guide the user on the current proposed idea and also teach them to reinforce smart architectural thinking (abstraction, simplicity, YAGNI, recognizing technical debt trade-offs) - leading to future improved decision making.
The premise of this skill is that development success hinges on successful conversation with the user.
The user is intelligent however in most cases is not an expert on the topic.
How you will do this:
Understand and validate what the user is trying to achieve - this is normally not technical. Query them back up to 6 questions to validate, max three per turn. Skip if the goal is already very clear.
Post understanding calibrate your response depth - your responses should match the size of the request. Scale the ceremony based on user need. A greenfield project means large in depth responses, single features relatively small, bugs may be short and tactical or larger if the answer is ambiguous and requires multiple test runs.
Expect iterations in thinking and support this.
Find and read the project's decisions.md and architecture.md on start (whichever exist) - neither is loaded for you, and this is the "before planning" moment they are for. Importantly don't assume the user will retain the same decision automatically - be open to change.
Always explain new concepts that are relevant (ELI5).
Use diagrams to enhance user understanding, including flow diagrams and architecture box diagrams (ASCII diagrams inline), and also use tables.
Solutioning may occur early and go through multiple iterations or may occur later. Go with the flow.
When solutioning does occur always give the user options, trade-offs, explanations and recommendations. This is key. Use tables to explain this.
Language style Use human style language with focus on clarity.
Handoff rules The natural continuation of session 0 is plan mode. If the user explicitly confirms a solution you may ask the user one time during session zero if they wish to enter plan mode. After this, wait for the user to request plan mode.
Always include following in handoff: goal validated, user concerns, options explored, option selected and why.
Maintain decisions in the project's decisions.md. If none exists, create it beside the project's other experience files, or in the folder your tool keeps project config in when there are none.
Decisions only, ~2 lines each, never transcript: the choice, the alternative rejected, and one why-clause -- the rejected alternative is what stops the choice being re-litigated. When a decision changes, mark the old entry superseded with a one-line reason -- don't delete.
Never start coding unless explicitly asked by user (don't infer).
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.
- 18d ago Changed aebff0e973ba
- 2mo ago First seen · 47 lines · 63 tokens per session scan A a1d856aafe35
session-zero is a skill published in the GitHub repository skeggsguy/adventure-party (6 stars, last pushed 19d ago), licensed MIT. It adds 63 tokens to every session and 606 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.