Contextium Session Startup

VerifiedSafe

Runs the full Contextium session startup sequence by executing three agents in order: initializer, task determiner, and context fetcher. Helps set up the environment, check available tools, and load relevant context at the start of a session.

Sby Skills Guide Bot
ProductivityIntermediate
6/2/2026
Claude Code
#contextium#startup#agents#session-setup

Recommended for

Automated summary

Runs the full Contextium session startup sequence by executing three agents in cascade.

Strengths

  • Automated startup with environment verification and state creation
  • Clear pipeline: initialization, task determination, context loading
  • Separate logs per agent for easy debugging

Limitations

  • Only works within the Contextium framework
  • Requires correct setup of scripts and agents
  • Logs stored in /tmp are ephemeral
When to use it

At the beginning of every new Contextium session to initialize the environment and identify the current task.

When not to use it

For simple sessions or outside Contextium, where manual startup is sufficient.

Security analysis

Safe
Quality score85/100

The skill runs a local bash script './agents/run-startup.sh' to orchestrate a startup sequence. No destructive, exfiltration, or obfuscated commands are present. The script is not downloaded from an external source, and the command itself is straightforward. The risk of executing a local script is minimal given the trusted environment.

No concerns found

How this analysis is made

Examples

Initialize Contextium Session
Run the full Contextium session startup sequence.
Execute startup pipeline
Please execute the Contextium startup orchestrator to initialize this session.
Start agents for session
Run ./agents/run-startup.sh to initialize the environment, determine current task, and load context.

name: startup description: Run full Contextium session startup sequence with all agents allowed-tools: Bash, Read

Contextium Session Startup

Run the full startup agent pipeline to initialize this session.

Execution

Run the startup orchestrator:

./agents/run-startup.sh

This executes three agents in sequence:

  1. Initializer - Verify environment, create state files
  2. Task Determiner - Analyze state, determine current task
  3. Context Fetcher - Load minimal relevant context

After Startup

Review the output and:

  • Note the current task (if any)
  • Check for any missing tools
  • Review loaded context

Logs are available at:

  • /tmp/contextium-startup.log - Full startup output
  • /tmp/contextium/*.log - Individual agent logs

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/contextium-session-startup-mm5t8aki' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/contextium-session-startup-mm5t8aki/download' --output '.skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md.part' && mv '.skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md.part' '.skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash, Read

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md' && test -s '.skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/startup' && cp -R '.skill-downloads/contextium-session-startup-mm5t8aki' '.claude/skills/startup'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/contextium-session-startup-mm5t8aki'

openskills read 'contextium-session-startup-mm5t8aki'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/contextium-session-startup-mm5t8aki/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills