mentor-init

mentor-init is a command for coding agents from MartyBonacci/specswarm. It costs 101 tokens per session (929 once invoked), scanned A, original, MIT.

A setup command for creating a separate mentor directory that guides a headless builder, an automated coding process that works without direct interaction.

In plain words
What is it for?
Use it to set up mentor-led development, including prompts, builder settings, session instructions, audit trails, and one-builder-per-tree locks.
Why use it?
It gives the mentor process a defined role, escalation rules, idea storage, dispatch records, and controls for working with the builder's repository.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ss plugin — 10 skills, 34 commands, 6 agents, 4 hooks shipped together

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/martybonacci/specswarm/mentor-init
Clone the repo
git clone --depth 1 https://github.com/MartyBonacci/specswarm

Or install ss, the plugin that ships this one along with the rest of its 10 skills, 34 commands, 6 agents, 4 hooks.

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.

agentmods badge for mentor-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/martybonacci/specswarm/mentor-init.svg)](https://agentmods.dev/commands/martybonacci/specswarm/mentor-init)
Your own site
<a href="https://agentmods.dev/commands/martybonacci/specswarm/mentor-init"><img src="https://agentmods.dev/badge/commands/martybonacci/specswarm/mentor-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 929 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 $0.00101 $0.00929
Opus 5 $0.00051 $0.00464
Sonnet 5 $0.00020 $0.00186
Haiku 4.5 $0.00010 $0.00093

Measured 4d ago against content hash 0ed9c3ac742f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mentor-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 4d 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.

plugins/ss/commands/mentor-init.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecSwarm Mentor Init

Sets up the current directory as a mentor directory — the home of a mentor instance that drives a headless builder via /ss:conduct, and never writes the builder repo's application code itself.

The layout this creates (proven in the Custom Cult v3 pilot, ~500 dispatches):

<mentor-dir>/
├── MENTOR-KICKOFF.md          # the standing role — SessionStart hook injects it every session
├── process/
│   ├── escalation-boundary.md # what self-resolves vs subagent-verifies vs goes to the human
│   └── PARKING-LOT.md         # verbatim idea capture — the human never holds a mental note
├── dispatch/prompts/          # your authored slice prompts live here
├── .specswarm/conduct/
│   ├── config                 # BUILDER_DIR, MODEL, TIMEOUT, WATCH_PORTS
│   ├── runs/                  # every dispatch's audit trail
│   └── locks/                 # one-builder-per-tree, mechanically enforced
└── .claude/
    ├── settings.json          # SessionStart hook wired (merged, never clobbered)
    └── hooks/mentor-role.sh   # cats MENTOR-KICKOFF.md into session context

Steps

  1. Resolve inputs. If project_name or --builder-dir was not provided, ask the user (AskUserQuestion or plain prompt). The builder dir must be an existing git repo — typically the project checked out inside this mentor directory (e.g. ./my-app). If the intended builder repo doesn't exist yet, stop and have the user clone/create it first.

  2. Run the scaffold (idempotent — existing files are kept, never overwritten):

bash "${CLAUDE_PLUGIN_ROOT}/lib/conduct/scaffold.sh" \
  --project-name "<project_name>" \
  --builder-dir "<builder-dir>"
  1. Review with the user, then hand off. Walk them through what was created, then tell them:
    • Edit MENTOR-KICKOFF.md to taste — it's the live role text, read by the hook on every session start.
    • Confirm the Standing Authorizations in process/escalation-boundary.md (especially the push-without-approval checkbox — that's their call, not yours).
    • Set WATCH_PORTS in .specswarm/conduct/config if the project runs dev/e2e webservers.
    • Restart the Claude Code session in this directory so the SessionStart hook fires — from then on, every session opens already knowing it's the mentor.
    • First dispatch: /ss:conduct (it walks the prompt grammar).
    • Recommended: install the ss-status plugin from this marketplace and run /ss-status:install once — the statusline then shows background-builder state in real time (🔨 building / ✓ safe to close), answering "is anything running?" at a glance with no daemon to manage.

Read the full file on GitHub · 58 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. 4d ago First seen · 58 lines · 101 tokens per session scan A 0ed9c3ac742f

Subscribe to this mod's changes

mentor-init is a command published in the GitHub repository MartyBonacci/specswarm (65 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 929 once invoked, about $0.0005 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.