Dojo
Necmttn/ax
Surplus-quota training loop over the ax graph - the agent burns the remaining 5h/7d plan-quota window on self-improvement: locking pending verdicts, filling briefs, backtesting routing classes…
Autonomous trading loop for the MMR platform. An agent skill from 9600dev/mmr.
Install Mmr Loop Skill
$ npx skills add 9600dev/mmr --skill mmr-loop-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install 9600dev/mmr mmr-loop-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/9600dev/mmr.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mmr-loop-skill .claude/skills/mmr-loop-skill && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mmr-loop-skill" agent skill from https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skill into .claude/skills/mmr-loop-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmr-loop-skill", 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.
$skill-installer install https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skillType 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.
$ npx skills add 9600dev/mmr --skill mmr-loop-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install 9600dev/mmr mmr-loop-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/9600dev/mmr.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mmr-loop-skill .agents/skills/mmr-loop-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mmr-loop-skill" agent skill from https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skill into .agents/skills/mmr-loop-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmr-loop-skill", 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.
$ npx skills add 9600dev/mmr --skill mmr-loop-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install 9600dev/mmr mmr-loop-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/9600dev/mmr.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mmr-loop-skill .cursor/skills/mmr-loop-skill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mmr-loop-skill" agent skill from https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skill into .cursor/skills/mmr-loop-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmr-loop-skill", 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.
$ gemini skills install https://github.com/9600dev/mmr.git --path skills/mmr-loop-skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add 9600dev/mmr --skill mmr-loop-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install 9600dev/mmr mmr-loop-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/9600dev/mmr.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mmr-loop-skill .gemini/skills/mmr-loop-skill && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mmr-loop-skill" agent skill from https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skill into .gemini/skills/mmr-loop-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmr-loop-skill", 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.
$ gh skill install 9600dev/mmr mmr-loop-skillInstalls 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).
$ npx skills add 9600dev/mmr --skill mmr-loop-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/9600dev/mmr.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mmr-loop-skill .github/skills/mmr-loop-skill && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mmr-loop-skill" agent skill from https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skill into .github/skills/mmr-loop-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmr-loop-skill", 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.
$ npx skills add 9600dev/mmr --skill mmr-loop-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install 9600dev/mmr mmr-loop-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/9600dev/mmr.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mmr-loop-skill .opencode/skills/mmr-loop-skill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mmr-loop-skill" agent skill from https://github.com/9600dev/mmr/tree/master/skills/mmr-loop-skill into .opencode/skills/mmr-loop-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mmr-loop-skill", 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
mmr-loop-skill- GitHub stars
- 131
- Token cost
- ~2.6k tokens
- SKILL.md length
- 1,117 words
- Files
- 3 (incl. scripts, references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Autonomous trading loop for the MMR platform. An agent skill from 9600dev/mmr.
- Works in 11 steps: Proposals, not trades: The loop creates… → Position limits: Respects max_positions… → Group budgets: Checks group allocation… → …
- The user asks to start monitoring
- SKILL.md covers Where the loop's commands run, How It Works, Starting the Loop and User Interaction, plus 6 more sections
- Runs Python scripts from its folder; calls docker
What it does
Mmr Loop Skill is an agent skill from 9600dev/mmr. Autonomous trading loop for the MMR platform. Continuously monitors portfolio, scans for opportunities, creates trade proposals, and manages risk. Requires the 'mmr' skill to be loaded first. Use when the user asks to start monitoring, trading autonomously, or running a trading loop.
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/LOOP_CONFIG.md` and `scripts/loop_engine.py`).
It sits in Business, Finance & HR, covering Trading and backtesting and Proposals and quotes. It works with DuckDB. The repository describes itself as: Python based algorithmic trading platform for Interactive Brokers.
When your agent uses it
- The user asks to start monitoring
- Trading autonomously
- Running a trading loop
Example prompts
- “/mmr-loop-skill”
Requirements
- Python 3
- Docker
Workflow steps
11 steps, taken from the first numbered list in SKILL.md.
- Proposals, not trades: The loop creates proposals but NEVER auto-executes. You approve or reject.
- Position limits: Respects max_positions from position_sizing.yaml. Stops proposing at the limit.
- Group budgets: Checks group allocation budgets before proposing. Over-budget = warning, not block.
- Gates apply to OPENS only; exits are never refused: The risk gate, trading filter, leverage check, and any approval gate run on…
- Gates fail closed on opens (expect brief warm-up refusals after a restart): When a critical input can't be read (daily PnL, account value…
- Proposal state machine: Terminal statuses (EXECUTED / REJECTED / FAILED / EXPIRED) are immutable. If approve() fails at the broker (margin…
- Scanner fails loudly: ideas() with location= raises on "no results" rather than returning an empty list, so the loop will see a real error…
- Signed exposure in risk reports: portfolio_risk() returns net_exposure_pct, long_exposure_pct, short_exposure_pct alongside…
- Strategy gauntlet gate ("no hash, no live"): If the loop ever deploys or enables a strategy, an auto_execute strategy is refused without a…
- Opt-in approval hardening (default OFF — not on the running stack): Three Phase-2 defenses exist but ship disabled (see…
- Context management: Aggressive compaction keeps context at ~12K tokens. Can run indefinitely.
What it can do on your machine
Read from SKILL.md and the folder at commit 5ac9b3d. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
docker
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use docker, 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
Mmr Loop Skill loads about 2.6k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 1,117 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,117 words (~2,607 tokens).
“This skill turns the MMR trading platform into an autonomous trading agent. It implements a phased state machine that continuously monitors your portfolio, scans for opportunities, and creates trade proposals for your review.”
- name
- mmr-loop-skill
- metadata.author
- mmr
- metadata.version
- 1.0
- metadata.dependencies
- mmr-skill
Files
SKILL.md and 2 other files (scripts, references) in skills/mmr-loop-skill of 9600dev/mmr.
- SKILL.md
- references/LOOP_CONFIG.md
- scripts/loop_engine.py
Open the folder on GitHubat commit 5ac9b3d
Compare with similar skills
Mmr Loop Skill 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mmr Loop Skill this skill9600dev/mmr | 131 | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| DojoNecmttn/ax | 116 | — | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Strategy Pivot Designertradermonty/claude-trading-skills | 3k | 1 repos | ~856 | Automated safety check: Pass | MIT | |
| Backtestmarketcalls/vectorbt-backtesting-skills | 208 | 1 repos | ~1.1k | Automated safety check: Notes | None | |
| Vectorbt Expertmarketcalls/vectorbt-backtesting-skills | 208 | — | ~3.4k | Automated safety check: Notes | None | |
| Strategy Comparemarketcalls/vectorbt-backtesting-skills | 208 | 1 repos | ~595 | Automated safety check: Notes | None |
Similar skills
Strategy Pivot Designer
tradermonty/claude-trading-skills
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
Backtest
marketcalls/vectorbt-backtesting-skills
Quick backtest a strategy on a symbol. An agent skill from marketcalls/vectorbt-backtesting-skills.
Vectorbt Expert
marketcalls/vectorbt-backtesting-skills
VectorBT backtesting expert. An agent skill from marketcalls/vectorbt-backtesting-skills.
Strategy Compare
marketcalls/vectorbt-backtesting-skills
Compare multiple strategies or directions (long vs short vs both) on the same symbol.
Optimize
marketcalls/vectorbt-backtesting-skills
Optimize strategy parameters using VectorBT. An agent skill from marketcalls/vectorbt-backtesting-skills.
More from 9600dev/mmr
Mmr Skill
9600dev/mmr
Operate the MMR algorithmic trading platform on Interactive Brokers.
Mmr Verification
9600dev/mmr
The MMR safety-verification workflow — how to change trading-critical code without breaking the invariants that keep the book safe.
News
9600dev/mmr
Fetch, search, and summarize financial news articles via the local scraper service (~/dev/scraper) at http://127.0.0.1:8089.
Related
Works with
Categories
Questions about Mmr Loop Skill
What does Mmr Loop Skill do?
Autonomous trading loop for the MMR platform. An agent skill from 9600dev/mmr. Mmr Loop Skill is an agent skill from 9600dev/mmr. Autonomous trading loop for the MMR platform.
When should I use Mmr Loop Skill?
Mmr Loop Skill fits situations like: the user asks to start monitoring; trading autonomously; running a trading loop.
How do I install Mmr Loop Skill in Claude Code?
Run `npx skills add 9600dev/mmr --skill mmr-loop-skill -a claude-code`. Or copy the skill folder (skills/mmr-loop-skill in 9600dev/mmr) into .claude/skills/mmr-loop-skill in your project. Claude Code loads it when a task matches its description.
How do I install Mmr Loop Skill in Codex?
Run `npx skills add 9600dev/mmr --skill mmr-loop-skill -a codex`. Or copy the skill folder (skills/mmr-loop-skill in 9600dev/mmr) into .agents/skills/mmr-loop-skill in your project. Codex loads it when a task matches its description.
Can I use Mmr Loop Skill 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 9600dev/mmr --skill mmr-loop-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mmr-loop-skill, .gemini/skills/mmr-loop-skill, .github/skills/mmr-loop-skill and .opencode/skills/mmr-loop-skill in your project.
What does Mmr Loop Skill need to run?
Going by SKILL.md and its folder, Mmr Loop Skill needs Python for the scripts in its folder and the command-line tools its instructions call (docker). Our summary lists: Python 3; Docker.
Does Mmr Loop Skill access the network?
SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Mmr Loop Skill 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Mmr Loop Skill use?
Mmr Loop Skill has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Mmr Loop Skill use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 749 tokens, read only when the agent opens those files.
What are the alternatives to Mmr Loop Skill?
Skills that share tags, products or a category with Mmr Loop Skill: Dojo (Necmttn/ax, 116 stars), Strategy Pivot Designer (tradermonty/claude-trading-skills, 3k stars), Backtest (marketcalls/vectorbt-backtesting-skills, 208 stars) and Vectorbt Expert (marketcalls/vectorbt-backtesting-skills, 208 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mmr Loop Skill?
9600dev (a GitHub user) maintains it in 9600dev/mmr, which has 131 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 14, 2026.
Source: 9600dev/mmr on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.