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.
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace/plugin install credoWrote 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.
[](https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/session-init)<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.
<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>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 | $0.00010 | $0.01976 |
| Opus 5 | $0.00005 | $0.00988 |
| Sonnet 5 | $0.00002 | $0.00395 |
| Haiku 4.5 | $0.00001 | $0.00198 |
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.
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.
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.
- 10d ago First seen · 165 lines · 10 tokens per session scan A d9ddfab88899
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.
Other commands, from other repositories
migrate
Generate and manage database migrations.
context-stats
Display context window usage and token statistics.
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.