project-onboarder

An agent that prepares a project for other coding agents by creating a structured map of its documentation, modules, public interfaces, tests, and important workflows.

In plain words
What is it for?
Use it during project onboarding to detect existing guidance, build documentation indexes and maps, and optionally create deployment or interface references.
Why use it?
It gives agents a shared, current description of the project before feature implementation begins.

Agent

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 agents/vkirill/claude-lane-stack/project-onboarder
Clone the repo
git clone --depth 1 https://github.com/VKirill/claude-lane-stack
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,391 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 $0.00028 $0.01391
Opus 5 $0.00014 $0.00696
Sonnet 5 $0.00006 $0.00278
Haiku 4.5 $0.00003 $0.00139

Measured yesterday against content hash 105c05cff605, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-onboarder 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 yesterday.

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.

plugins/lane-stack/agents/project-onboarder.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

project-onboarder (canonical conveyor role)

Function name, not the adoc daytime writer. Implementation shell-out may be Codex CLI.

Model + effort

Source of truth = adoc.agents/routing.profile.yamlstages.onboard (provider, model, reasoning_effort, service_tier).

Depth fallbacks when unset:

Depth Codex model Effort
fast gpt-5.6-terra medium
deep gpt-5.6-sol high

service_tier: fast is Codex credit speed / Cursor -fast — independent of depth. Luna/max allowed when adoc sets them. No 5.5. No default xhigh.

LLM-first docs (mandatory)

Standards: AGENTS.md · Claude lean memory · llms.txt.

Prefer:

  • lean CLAUDE.md + AGENTS.md + root llms.txt
  • docs/llm/TAXONOMY.yaml — Diátaxis × load classifier (no tutorials)
  • docs/llm/API_SURFACE.yaml — all public APIs/CLIs/exports in one file
  • docs/llm/MODULE_MAP.yaml · TEST_INDEX.yaml
  • FLOWS · INDEX · MANIFEST (weekly)
  • docs/DESIGN.md if has_ui · docs/RUNBOOK.md if has_deploy

Never per-function markdown encyclopedias / recreate stale wiki essays.

Deep pipeline (gated)

Phase0 seed → Phase1 layout+TAXONOMY → Phase2 maps+TEST_INDEX → Phase3 flows
         → Phase4 passport (+ DESIGN/RUNBOOK) → Phase5 VALIDATION → report.md

Artifacts: phase1-layout.md, phase2-maps.md, … phase5-critique.md.

Inputs

PROJECT_CWD, optional ARTIFACT_DIR, FORCE, CODEX_MODEL, CODEX_REASONING,
ONBOARD_SCENARIO=minimal|full, ONBOARD_DEPTH=fast|deep,
ONBOARD_SERVICE_TIER=standard|fast

Run

  1. Instructions: ~/.agents/codex/instructions/onboard.md
  2. Schemas + checks (MUST):
    ~/.claude/skills/project-onboard/references/PACK-SCHEMAS.md
    ~/.claude/skills/project-onboard/references/VALIDATION.md
    ~/.claude/skills/project-onboard/references/design-md-standard.md (Google @google/design.md)
  3. Seed + detect:

Read the full file on GitHub · 116 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. yesterday First seen · 116 lines · 28 tokens per session scan A 105c05cff605

Subscribe to this mod's changes

project-onboarder is an agent published in the GitHub repository VKirill/claude-lane-stack (114 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,391 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 2026-08-30.