Skip to content
Agentmart
Submit a tool

comptext-local-autonomy

Offline local-only autonomous workflow in CompText.

Skill by ProfRandom92

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying comptext-local-autonomy?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/profrandom92-comptext-local-autonomy

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Offline local-only autonomous workflow in CompText.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/comptext-local-autonomy

What's inside

Skill name
comptext-local-autonomy
Description
Offline local-only autonomous workflow in CompText.
License
Apache-2.0
Instructions
33 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# CompText Local Autonomy Skill

This skill guides the one-unit-at-a-time offline development workflow within the `comptext` repository.

## Safe Autonomous Workflow Loop

Always operate using a strict step-by-step loop:

1. **Inspect**: Read the request, look up existing implementation patterns, and verify the current codebase status.
2. **Plan**: Write down the exact steps to implement, including safety boundaries and validation strategy.
3. **Implement**: Write or edit the code local-only. Focus on exactly one logical unit at a time.
4. **Test**: Run focused tests for the changed files.
5. **Validate**: Run repository-wide checks:
   - `python -m pytest`
   - `git diff --check`
6. **Commit**: If validation passes, create a single clean local commit.
7. **Stop**: Finish and report the status.

## Required Validation
Before finishing or proposing any commit, ensure these commands pass cleanly:
- Focused tests for the modified module
- `python -m pytest` for full suite validation
- `git diff --check` to verify no whitespace or conflict marker issues

## Forbidden Behavior
To ensure local dry-run safety, the following actions are strictly forbidden:
- **No Network / Provider Calls**: Never communicate over network or invoke external LLM provider APIs.
- **No GitHub Writes / PRs**: Do not push branches, open pull requests, merge, or call GitHub APIs.
- **No Secrets / Env Access**: Do not read `.env` files, environment variables, or retrieve secrets.
- **No Server Operations**: Do not start background servers or bind network ports.
- **No Broad Docs Expansion**: Do not bloat or write unnecessary documentation. Keep documentation changes precise.

From ProfRandom92/Comptext, Apache-2.0.

More from ProfRandom92/Comptext

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 9, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ProfRandom92

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get comptext-local-autonomy running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying comptext-local-autonomy?

CallGet help
Cite this page

comptext-local-autonomy skill. Agent Mart. https://agentmart.dev/skills/profrandom92-comptext-local-autonomy (last updated 2026-10-24)