Install the "feature-loop" agent skill from https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop into .claude/skills/feature-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-loop", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add DemonDamon/AgenticX --skill feature-loop -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "feature-loop" agent skill from https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop into .agents/skills/feature-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-loop", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add DemonDamon/AgenticX --skill feature-loop -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "feature-loop" agent skill from https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop into .cursor/skills/feature-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-loop", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add DemonDamon/AgenticX --skill feature-loop -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "feature-loop" agent skill from https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop into .gemini/skills/feature-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-loop", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add DemonDamon/AgenticX --skill feature-loop -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "feature-loop" agent skill from https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop into .github/skills/feature-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-loop", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add DemonDamon/AgenticX --skill feature-loop -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "feature-loop" agent skill from https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/bundled/feature-loop into .opencode/skills/feature-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-loop", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
feature-loop
GitHub stars
294
Token cost
~791 tokens
SKILL.md length
358 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
Apache-2.0
At a glance
Coding agent for the project-level harness — one feature per session, must verify, must be mergeable.
Works in 3 steps: One feature per session. Multiple… → Always verify before commit.… → Keep the branch mergeable. Each commit…
AI & LLM Engineering work in your project
SKILL.md covers Iron rules, Loop, Failure modes and Forbidden
Calls git
What it does
Feature Loop is an agent skill from DemonDamon/AgenticX. Coding agent for the project-level harness — one feature per session, must verify, must be mergeable.
Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. The repository describes itself as: AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers… The licence is Apache-2.0.
When your agent uses it
AI & LLM Engineering work in your project
Example prompts
“/feature-loop”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
1One feature per session. Multiple in_progress features are forbidden by the store; do not bypass.
2Always verify before commit. feature_complete rejects features that have not been promoted to verified via verify_run.
3Keep the branch mergeable. Each commit must compile, pass verify.yaml, and not depend on uncommitted local state.
What it can do on your machine
Read from SKILL.md and the folder at commit c1af2c7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Feature Loop loads about 791 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 358 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~29
When it runs· the whole SKILL.md, loaded when a task matches
~791
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Use when session_mode == feature_loop and the project is past the Initializer phase (system prompt will say "Coding 阶段").
Iron rules
One feature per session. Multiple in_progress features are forbidden by the store; do not bypass.
Always verify before commit.feature_complete rejects features that have not been promoted to verified via verify_run.
Keep the branch mergeable. Each commit must compile, pass verify.yaml, and not depend on uncommitted local state.
Loop
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.
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.
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.
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.
Commit via shell.
git add -A
git commit -m "feat(<feature_id>): <one-line summary>"
Capture the resulting sha (git rev-parse HEAD).
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.
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.
Show full SKILL.md (90 more words)Show less
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.
Feature Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
A skill your agent uses when scanning an arbitrary Git repository to create, refresh, or selectively update Markdown summaries of code modules, especially when changes must be traced from each…
Guide for using the A2A (Agent-to-Agent) communication protocol in AgenticX including agent discovery, skill invocation, remote agent cards, and distributed agent systems.
Guide for deploying AgenticX agents to production including Docker containerization, Kubernetes orchestration, Volcengine AgentKit cloud deployment, and API server setup.
Guide for setting up and using the AgenticX memory system including Mem0 integration, long-term memory, context management, and memory-enhanced agents.
A skill your agent uses when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come…
Coding agent for the project-level harness — one feature per session, must verify, must be mergeable. Feature Loop is an agent skill from DemonDamon/AgenticX. Coding agent for the project-level harness — one feature per session, must verify, must be mergeable.
When should I use Feature Loop?
Feature Loop fits situations like: AI & LLM Engineering work in your project.
How do I install Feature Loop in Claude Code?
Run `npx skills add DemonDamon/AgenticX --skill feature-loop -a claude-code`. Or copy the skill folder (agenticx/skills/bundled/feature-loop in DemonDamon/AgenticX) into .claude/skills/feature-loop in your project. Claude Code loads it when a task matches its description.
How do I install Feature Loop in Codex?
Run `npx skills add DemonDamon/AgenticX --skill feature-loop -a codex`. Or copy the skill folder (agenticx/skills/bundled/feature-loop in DemonDamon/AgenticX) into .agents/skills/feature-loop in your project. Codex loads it when a task matches its description.
Can I use Feature Loop in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DemonDamon/AgenticX --skill feature-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-loop, .gemini/skills/feature-loop, .github/skills/feature-loop and .opencode/skills/feature-loop in your project.
What does Feature Loop need to run?
Going by SKILL.md and its folder, Feature Loop needs the command-line tools its instructions call (git).
Does Feature Loop access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Feature Loop safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Feature Loop use?
Feature Loop is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Feature Loop use?
About 791 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Feature Loop?
Skills that share tags, products or a category with Feature Loop: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Feature Loop?
DemonDamon (a GitHub user) maintains it in DemonDamon/AgenticX, which has 294 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.
Source: DemonDamon/AgenticX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
