A first-use interview that records a researcher’s preferences, beliefs, working methods, and rejected approaches in files the agent can use later. The resulting index is automatically added to future sessions.

Use it to create or refresh a research taste profile, choose a short or deep interview, and update individual sections when views change.

It gives the agent durable context about how the researcher judges ideas and writing, so that context does not have to be re-explained every time.

onboard — Skill for Claude Code by Rockielab

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.

Any agent

npx skills add Rockielab/rockie-claude --skill onboard

Clone the repo

git clone --depth 1 https://github.com/Rockielab/rockie-claude

Made for: Claude Code.

Or install rockie-claude, the plugin that ships this one along with the rest of its 29 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rockielab/rockie-claude/onboard/github.svg)](https://agentmods.dev/skills/rockielab/rockie-claude/onboard)

Your own site

<a href="https://agentmods.dev/skills/rockielab/rockie-claude/onboard"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/onboard/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rockielab/rockie-claude/onboard"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,565 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.

Model	Per session	Once invoked
Fable 5.1	$0.00117	$0.01565
Opus 5	$0.00059	$0.00783
Sonnet 5	$0.00023	$0.00313
Haiku 4.5	$0.00012	$0.00156

Measured 11d ago against content hash d38756c0ce77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

onboard 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.

The scan reads SKILL.md. This mod also ships 2 executable files (runtime/compile.py, runtime/test_lab_charter_prompt.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

onboard — 95% identical, 2 lines differ

project-harness/skills/onboard/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/onboard — researcher taste interview

The marquee onboarding skill. Produces a durable, agent-injectable record of who the researcher is, what they believe, how they judge work, and what dead ends they refuse to revisit.

Sister to AGENTS.md. AGENTS.md says what to do in this repo. The taste/ corpus says who this researcher is — installed per-repo today, with cross-repo portability planned (symlink ~/.rockie/taste/ → <repo>/.rockie/taste/ is the recommended manual interim).

When to run

First-run — SessionStart hook flags absence of .rockie/taste/INDEX.md; agent suggests /onboard.
Explicit invocation — user types /onboard.
Refresh — /onboard --redo rewrites everything; /onboard --section <soul|style|methodology|dismissals> refreshes one file.
Deep mode — /onboard --deep runs Tier 2 (20–30 min, voice-first laddering). Otherwise Tier 1 (5–7 questions, ~5 min).

What the skill does

Loads prompts/interviewer-tier1.md (or interviewer-tier2.md if --deep) into the active agent's system context.
The agent runs the interview turn-by-turn following the prompt's phase-gated state machine. The user answers via text or /voice tap.
As the interview progresses, the agent writes intermediate state to .rockie/taste/.draft.json after every turn (so the session can be resumed if interrupted).
When coverage reaches the end-condition, the agent emits a summary round, asks the user to confirm or correct, then runs runtime/compile.py to produce the six markdown files in .rockie/taste/.
The agent opens INDEX.md in the user's editor for final review, then commits the corpus.

Hard rules

One question per turn. The interviewer prompt enforces this with a question-mark self-check; the agent must respect it.
Never press a dodged question. Mark SOFT in the scratchpad and move on. Pressing produces confabulation, not truth.
Never silently rewrite an existing taste file. /onboard --redo is explicit; the agent cannot decide to overwrite SOUL.md unprompted. (MEMORY.md and DISMISSALS.md are append-only and may be written to by Stop-hook flow, not this skill.)
Never invent answers. If the user is short on a topic, the generated file marks the topic as [SOFT — needs deepening] rather than embellishing.
Voice opt-in only. Tier 1 is text-default; Tier 2 prompts the user to /voice tap for each answer if they want, but never requires it.

Read the full file on GitHub · 134 lines

Files

What ships with it

15 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.

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.

11d ago First seen · 134 lines · 117 tokens per session scan A d38756c0ce77

Subscribe to this mod's changes

onboard is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,565 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.

Claude Code Memory and context Research agent-harness ai-research anthropic autonomous-research claude

session-judgment-mining

A Japanese-language workflow for examining past Claude Code session files and turning repeated user decisions into reusable skills, rules, or Architecture Decision Records.

shimo4228/claude-harness · 336 tokens

rules-distill

Scan installed skills to extract principles that belong in the always-loaded rules layer (environment-specific facts, wiring, and traps — not general principles the substrate already applies) and distill them into rules — append to, revise, or create rule files. Use when the user says "distill rules"…

shimo4228/claude-harness · 123 tokens

wiki-query

A query tool for an Obsidian vault, which is a folder of linked Markdown notes, including a wiki of concepts and research notes. It combines information from several notes and includes links back to its sources.

shimo4228/claude-harness · 191 tokens

write-terva-lore

Author terva lore. Lore is context that a person authors in files. terva injects it only when it is keyword-relevant, or always-on. Use to create/add/write lore, "world info", a lorebook entry, keyed background, or a book of facts for a character.

terva-sh/terva · 66 tokens

handoff

Compact the current session into a handoff document. A fresh session or another agent can pick it up with no need to re-derive context. Use when asked to hand off, hand over, wrap up for another session or agent, or park work mid-stream.

terva-sh/terva · 56 tokens

retrospective

Distill the reusable lessons of this session into the durable homes that shape future sessions. The lessons are corrections, conventions you discovered, and traps you hit. The homes are the project or global AGENTS.md, a project skill, and memory when available. Use when asked for a retro, to capture or remember…

terva-sh/terva · 76 tokens