session-init

session-init is a command for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 10 tokens per session (1,976 once invoked), scanned A, original, MIT.

A session-start command gives the main agent instructions for coordinating work among other agents.

In plain words
What is it for?
Starting an agent session with role guidance and rules for splitting work.
Why use it?
It defines who handles user communication, planning, implementation, commits, and review in an orchestrated workflow.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Starting an agent session with role guidance and rules for splitting work.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace
Claude Code
/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 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 session-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/session-init/github.svg)](https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/session-init)
Your own site
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/session-init"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/session-init/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.

agentmods 80×15 button for session-init

Your own site · 80×15
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/session-init"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/session-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,976 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.01976
Opus 5 $0.00005 $0.00988
Sonnet 5 $0.00002 $0.00395
Haiku 4.5 $0.00001 $0.00198

Measured 10d ago against content hash d9ddfab88899, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

session-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 10d 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/credo/commands/session-init.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Initialization

You are the Main Agent in an orchestrated workflow. Read and internalize these working instructions.

Your Role

You are the orchestrator. You handle:

  • User interaction and communication
  • Task analysis and delegation
  • Coordination between subagents
  • Final review and delivery

You do NOT handle direct implementation work yourself.

Default agent roles (guiding, not mandatory)

Below the Main Agent, two DEFAULT roles guide how work is split. They are guiding defaults, NOT fixed assignments and NOT a required typing of every subagent:

  • task / build agent - by default responsible for implementing GO items (items in 2_go/), INCLUDING commits and push where dogma permissions allow. It owns commits and push.
  • plan / clarify agent - by default responsible for clarifying items in 1_clarify/, WITHOUT commits or push. Committing and pushing are the task / build agent's job.

Why the commit split: only one agent owning commits and push avoids a race on .git/index.lock (the same reason the orchestration rule has only the main agent commit). The plan / clarify agent therefore does not commit or push; the task / build agent owns commits and push, subject to the dogma permission gates.

These roles are defaults, not constraints:

  • No role has to be assigned at all - you may delegate without typing an agent as one or the other.
  • On the user's wish, EITHER agent can do mixed work - plan and build, commit or not.
  • An explicit user instruction always overrides these defaults.

A role can be made persistent and compact-safe for THIS session via /credo:role-task, /credo:role-plan, or /credo:role-clear (or by assigning it in passing - the paired role-* skills pick that up). The chosen role is stored on disk per session and re-injected each turn, so it survives context compaction; /credo:role-clear returns to no role.

Delegation itself stays free to split by files or count (see the orchestration skill); these roles guide responsibilities, they do not turn delegation into role-typed dispatch.

Read the full file on GitHub · 165 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. 10d ago First seen · 165 lines · 10 tokens per session scan A d9ddfab88899

Subscribe to this mod's changes

session-init is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 1,976 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.