init

A command for setting up project planning records and documenting the human team, their roles, and how to escalate decisions.

In plain words
What is it for?
Use it after bootstrapping the operating model to inspect the repository, fill the project profile, confirm inferred facts, and prepare the vision and delivery workflow.
Why use it?
It replaces a blank or unverified plan with information found in the repository, while keeping guesses clearly marked until an accountable person confirms them. It avoids inventing goals or progress.

Command

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/jpantsjoha/ai-native-developer-experience/init
Clone the repo
git clone --depth 1 https://github.com/jpantsjoha/ai-native-developer-experience
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00016 $0.00505
Opus 5 $0.00008 $0.00253
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00002 $0.00051

Measured 2d ago against content hash af66cecb21c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 2d 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.

commands/init.md · 37 lines

What it actually says

Initialise the project's delivery-planning records and human side of the harness. Skills supply capability; named humans supply authority.

  1. Run /join-the-team:bootstrap first, including its dry-run. This is safe for an existing adoption: matching operating files are unchanged, existing project planning records are preserved, and missing vision/workflow/roadmap/status/changelog files are seeded. Stop on a reported operating-contract or adapter conflict.
  2. If the repo already has code, run the read-only inspection pass to pre-fill what the repository reveals instead of presenting a blank form: python3 .agents/skills/operating-model-bootstrap/scripts/inspect_repo.py . Transcribe each finding into the profile as its inferred — source: …; confirm: … marker, then confirm them one at a time with the accountable human. Never promote an inferred value to a verified fact without confirmation; the profile cannot go active while any inferred field remains.
  3. Ground the vision and delivery workflow from verified project evidence. Leave roadmap outcomes and status claims unpopulated until the Product Owner validates them; never turn template placeholders into invented progress.
  4. Ask the user for each team member, one at a time:
    • name or handle;
    • role — offer the standard set: accountable operator, product owner, data owner, integration owner, domain reviewer, governance/docs reviewer;
    • accountable scope (e.g. which data domain, which requirements area);
    • escalation channel (GitHub @mention, chat handle, or other).
  5. Fill the profile's Team roster and escalation table with the answers. Keep any unfilled seat as an explicit not yet established — owner: <role>; required before: <trigger> placeholder — never invent a person or a scope.
  6. Reconcile the profile's Authority and approval roles table and escalation path with the roster so the two agree.
  7. Run /join-the-team:validate and report the result.
  8. Remind the user: roster seats are humans, not agents; an agent may route a question to a seat but can never hold one. Insufficient evidence = lane stops and the seat is tagged; silence never converts to permission.
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. 2d ago First seen · 37 lines · 16 tokens per session scan A af66cecb21c7

Subscribe to this mod's changes

init is a command published in the GitHub repository jpantsjoha/ai-native-developer-experience (11 stars, last pushed 25d ago), licensed Apache-2.0. It adds 16 tokens to every session and 505 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.