Feature Loop logo

Feature Loop

Community
DemonDamon
feature-loop

Coding agent for the project-level harness — one feature per session, must verify, must be mergeable.

Overview

PublisherDemonDamon
RepositoryAgenticX
Skill namefeature-loop
Stars
608
Forks
68
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by DemonDamon on GitHub. Read the source before you install it.

Installation

Install the Feature Loop AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/DemonDamon/AgenticX.git /tmp/AgenticX
mkdir -p .claude/skills
cp -r /tmp/AgenticX/agenticx/skills/bundled/feature-loop .claude/skills/feature-loop
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Feature Loop in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Feature Loop on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Feature Loop is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Feature Loop

Use when session_mode == feature_loop and the project is past the Initializer phase (system prompt will say "Coding 阶段").

Iron rules

  1. One feature per session. Multiple in_progress features are forbidden by the store; do not bypass.
  2. Always verify before commit. feature_complete rejects features that have not been promoted to verified via verify_run.
  3. Keep the branch mergeable. Each commit must compile, pass verify.yaml, and not depend on uncommitted local state.

Loop

  1. Sync from disk. Call project_status first thing every session — it reads feature_list.json / status.json / progress.md and reseeds your understanding from the single source of truth.
  2. Pick a feature.
    • If status.active_feature_id is already set, resume that one (the prompt block will tell you).
    • Otherwise call feature_select with no arguments to auto-pick the highest-priority pending feature with satisfied dependencies, or pass feature_id when the user names one.
  3. Implement using code_dev phases (Explore → Read → Author):
    • Explore with code_outline, grep, optional code_search.
    • Read with file_read slices (start/end line). Track files you have read in scratchpad.
    • Author with file_write skeletons first, then section-by-section appends.
  4. Run the gate. Call verify_run feature_id=<id>. If any step fails:
    • Do not call feature_complete.
    • Log a progress_append with the failing step name and root cause.
    • Decide: fix and rerun verify_run, or escalate to the user with the specific failure.
  5. Commit via shell.
    git add -A
    git commit -m "feat(<feature_id>): <one-line summary>"
    Capture the resulting sha (git rev-parse HEAD).
  6. Promote to committed. Call feature_complete feature_id=<id> commit_sha=<sha>. The store writes an immutable archive snapshot under .agx/project/archive/feature_<id>.json.
  7. Decide next step. Either call feature_select for the next feature in the same session, or stop and tell the user the loop closed cleanly.

Failure modes

  • verify_run timeouts: do not retry blindly. Inspect the log under .agx/project/archive/, fix the root cause, then rerun.
  • Dependency missed: feature_select will reject features whose depends_on isn't committed. Either pick a different feature or finish the prerequisite first.
  • Lost context after window compaction: re-call project_status. Disk is the source of truth.
  • Cold start (new machine, fresh session): project_status + feature_select is enough to resume. No memory of previous turns is required.

Forbidden

  • Editing files inside .agx/project/archive/ (immutable).
  • Calling project_init outside the Initializer phase.
  • Skipping verify_run because "tests are too slow".

Frequently asked questions

What does the Feature Loop AI skill do?

Coding agent for the project-level harness — one feature per session, must verify, must be mergeable.

Why use Feature Loop on TypingMind?

Because you install it once and use it with any model. Feature Loop is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Feature Loop in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Feature Loop?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Feature Loop?

As many as you like. As long as a model supports skills, you can use Feature Loop with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Feature Loop AI skill free?

Yes. It is published on GitHub by DemonDamon under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇