session-active

session-active is a skill for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 126 tokens per session (4,988 once invoked), scanned A, original, MIT.

A set of rules for an active Credo session, where the user is present and the agent collaborates with them in real time. It defines the shared behavior for this session mode.

In plain words
What is it for?
Use it when a Credo session is explicitly running in active mode. It governs live collaboration and the common rules shared by Credo session modes.
Why use it?
It gives the agent consistent guidance about how to work with the user during an active session. It also distinguishes active mode from passive and autonomous modes.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

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 Use it when a Credo session is explicitly running in active mode. It governs live collaboration and the common rules shared by Credo session modes.

Compare 6 skills 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-active

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/session-active"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/session-active.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,988 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00126 $0.04988
Opus 5 $0.00063 $0.02494
Sonnet 5 $0.00025 $0.00998
Haiku 4.5 $0.00013 $0.00499

Measured 11d ago against content hash b371a04e75f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

session-active scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

topic is empty (ntfy not configured) or curl is missing, the helper is a silent no-op (exit 0)
plugins/credo/skills/session-active/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

session-active - intensive live collaboration

A credo session runs in exactly one mode - active, passive, or autonomous - set by the /credo:session-active|passive|autonomous commands and surfaced on every prompt by the session-mode inject line. This skill is the umbrella for active mode: the user is present and you collaborate intensively and live. It ties the credo building-block skills together for this mode; it does not restate their rules.

This file also holds the canonical common core that all three session skills share. session-passive and session-autonomous reference this section instead of repeating it - read it there too.


Common core (shared by all three session skills)

These rules hold in every mode. The mode-specific sections only add or narrow behavior on top of this core. The core is deliberately thin: most of it points at a credo building-block skill that owns the actual rule, so nothing is duplicated.

One mode at a time

The three modes are exclusive - exactly one is active per session, bound to this session's id and surfaced by the inject line. Switching mode is an explicit user act via the /credo:session-* commands (which also couple the keep-alive autonomy flag). Do not assume a mode; read the inject line.

CLARIFY-FIRST

Ask until EVERYTHING is clear. Never assume prematurely that a request is clear. A GO happens only after EXPLICIT user confirmation.

  • Vague or open requests (for example "implement an obsidian memory graph view") are first researched - including on the internet where useful - and then clarified with the user: offer explanations, proposals, and a recommendation, do not silently pick one.
  • Clarify anything that is not unambiguous. A whole feature NEVER proceeds without a clarify round unless it is already GO.
  • Trivial, self-evident fixes need no question - a syntax error on line 10 is just fixed.
  • Before asking a clarify question about an EXISTING item - or judging it "still open" - read the WHOLE item body plus the requirements log (.credo/process/requirements/*.md): a stale head can read open when the point is already clarified and locked. Do not re-ask what is already answered there (read/build-gate + Body-freshness invariant, credo items skill).
  • The clarify gate is carried physically by the item folders: only 1_todo/2_go is buildable, 1_todo/1_clarify is not. See the credo items skill (the go-gate, C9).

Read the full file on GitHub · 386 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. 11d ago First seen · 386 lines · 126 tokens per session scan A b371a04e75f6

Subscribe to this mod's changes

session-active is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 126 tokens to every session and 4,988 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.