session-autonomous

session-autonomous is a command for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 24 tokens per session (891 once invoked), scanned A, original, MIT.

A session command that sets the persistent credo mode to autonomous.

In plain words
What is it for?
Starting an autonomous session with rules for pausing when idle and stopping autonomy when a real user message arrives.
Why use it?
It enables keep-alive behavior and records the directory as opted in, but is intended only when full autonomy has been explicitly allowed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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 autonomous session with rules for pausing when idle and stopping autonomy when a real user message arrives.

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-autonomous

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/session-autonomous"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/session-autonomous.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 891 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 $0.00024 $0.00891
Opus 5 $0.00012 $0.00445
Sonnet 5 $0.00005 $0.00178
Haiku 4.5 $0.00002 $0.00089

Measured 12d ago against content hash 4f62702756be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

session-autonomous 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 12d 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-autonomous.md · 56 lines

What it actually says

Session Mode: autonomous

Set the persistent, per-session credo mode to autonomous.

Use this ONLY when full autonomy plus AFK has been explicitly granted.

  1. Run: ${CLAUDE_PLUGIN_ROOT}/hooks/session-mode-set.sh autonomous This writes the per-session state (keyed by the current session_id) and turns keep-alive ON (sets credo-autonomy-active, lifts the credo-autonomy-paused opt-out). Keep-alive is hook-enforced: a registered Stop hook blocks a stop that has no scheduled ScheduleWakeup and instructs the model to set one, and a registered UserPromptSubmit hook turns autonomy off on any real user message (see the loaded skill).
  2. Remember this directory as opted-in (persistent, per-directory), so a future session here skips the onboarding ASK - the same effect as accepting the ASK: ${CLAUDE_PLUGIN_ROOT}/scripts/credo-dir-decision.sh set accepted
  3. Suspend-on-idle directive (durable, per session). If this invocation's argument (or a natural-language user statement) contains an explicit suspend-on-idle order - "suspend when done", "power down at the end", "hibernate afterwards", German "am Ende suspend", "danach runterfahren" - record it durably: ${CLAUDE_PLUGIN_ROOT}/scripts/credo-suspend-directive.sh set If it instead REVOKES a standing order - "no suspend", "leave it on", German "kein suspend", "lass an" - clear it: ${CLAUDE_PLUGIN_ROOT}/scripts/credo-suspend-directive.sh clear If there is NO argument and no such statement, do NOT touch an existing directive - it persists across re-invokes and compaction (that persistence is the point). The directive is only meaningful in autonomous mode; it gates the end-of-run power-down together with the sleep config and OVERRIDES sleep.enabled: false when set (see the session-autonomous skill). Do NOT set it from mere user presence or a casual remark - only an explicit order.
  4. Load the skill session-autonomous and follow its rules strictly (budget caps, ntfy per task and question, ScheduleWakeup plus wake marker, compact-plus).
  5. Load the items skill now (the credo work-item model and done-gate), UNLESS it is already active in your current context - do not reload it if you already have it. This puts the item model and go-gate in context before you act on approved GO items.
  6. Give the autonomous-start read-back per the session-autonomous skill ("Budget-start read-back"). Full four-part read-back on the FIRST start; on every invocation - including this one - emit AT LEAST the three-axis short form and NEVER start without it:
    • Budget: the binding axis + both live figures (5h% and weekly%).
    • Suspend/hibernate: the end-of-run posture (one line), DERIVED FROM the persisted suspend directive plus the sleep config - a set directive means you WILL power down at end-of-run provided sleep.command exists (overriding sleep.enabled: false); announced = committed.
    • ntfy: whether it is active and what will be reported (normally every go -> done item completion, plus come-to-PC pushes) - or that it runs silent if unconfigured.
  7. Read the approved GO order back verbatim before you start.
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. 12d ago First seen · 56 lines · 24 tokens per session scan A 4f62702756be

Subscribe to this mod's changes

session-autonomous is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 891 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.