Index of every page on this site: llms.txt
All skills
morluto avatar

/internalcot

@b574015
by morlutomorluto/internalcot22 stars
2
Run it yourself

Activate a persistent visible-reasoning mode that requires detailed internalcot CLI notes before substantive tools and answers, throughout the conversation. Use only when the user explicitly invokes $internalcot, says "internalcot on", or asks to enable internalcot mode. Keep it active until the user explicitly turns it off. Do not trigger merely because a user asks to think carefully, reason deeply, or show work.

Use this Skill: https://skilld.dev/gh/morluto/internalcot/internalcot

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈108 tokens for metadata: the name and description. ≈255 when used: this file. ≈62 more on demand in 1 file.

Description uses 5.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈431 characters, or 5.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

InternalCoT

Install the CLI and this skill together with:

npx internalcot@latest setup

This file is a stable discovery skill. The installed CLI owns the version-matched workflow instructions.

Load the current workflow

When this skill is invoked:

  1. Prefer the persistent CLI and run this standalone command before substantive work:

    internalcot skill

  2. If that command is unavailable or does not support skill, load the same workflow without installing anything globally:

    npx --yes internalcot@latest skill --npx

  3. Treat the returned Markdown as mandatory instructions for the selected CLI version. Follow every required note call for the current conversation, including any substantive task in the invocation message; do not replace the workflow with ordinary commentary or a shorter summary.

  4. If both commands fail, do not improvise an older workflow or claim the mode is active. Give the exact recovery command npx internalcot@latest setup.

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

1 warning2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill installs and executes a local command-line tool to manage visible working notes. It fetches its operational instructions dynamically from this tool at runtime.

  • Socket2mo

    1 alert: gptSecurity

  • Snyk2mo

    Risk: LOW · No issues

Provenance

Signed by skilld at b574015. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 weeks ago.

Steadyupdated 3 months ago

README badge

README badge for morluto/internalcot