by ttttonyhe
✊ Let your agent grind 24x7 fully autonomously
# Add to your Claude Code skills
git clone https://github.com/ttttonyhe/autogrind-skills
Tell your agent to start working. Walk away. Come back to finished work.
AutoGrind is a skill for AI coding agents that makes them work continuously and autonomously, grinding through improvements, fixes, tests, and polish in repeating cycles until you say stop. No hand-holding. No "should I continue?" No stopping because the TODO list looks empty.
Works for any long-running workflow: code, ML, research, design, writing.
Compatible with the Agent Skills open standard; works across Claude Code, Codex, Gemini CLI, OpenCode, Cursor, Windsurf, Roocode, Cline, Trae, Kimi Code, GitHub Copilot, Goose, AmpCode, Kilo, Kiro, Factory, Hermes Agent, and any skills-compatible agent. Each mechanism is grounded in published AI/ML research; see RESEARCH.md.
Paste this into any agent chat:
Please install the AutoGrind skill from https://github.com/ttttonyhe/autogrind-skills.
Clone the repo, install the autogrind/ skill to the right location for my agent environment,
and confirm it is ready to use.
Then invoke it:
/autogrind
Remember to enable unrestricted tool use so AutoGrind can run commands, read files, and commit without per-call permission prompts. For example:
claude --dangerously-skip-permissions
Without this, AutoGrind pauses on every tool call. It works, but defeats the purpose.
All agentskills.io-compatible agents discover skills from ~/.agents/skills/. One install, all agents:
No comments yet. Be the first to share your thoughts!
git clone https://github.com/ttttonyhe/autogrind-skills.git
cd autogrind-skills
# Symlink (live updates from this repo)
ln -sfn "$(pwd)/autogrind" ~/.agents/skills/autogrind
# Or copy for a stable install
cp -r autogrind ~/.agents/skills/autogrind
# Symlink (live updates from this repo)
ln -sfn "$(pwd)/autogrind" ~/.claude/skills/autogrind
# Or copy for a stable install
cp -r autogrind ~/.claude/skills/autogrind
Invoke: /autogrind or "keep working, don't stop"
cp -r autogrind ~/.agents/skills/autogrind
Codex discovers skills automatically. Enable full auto-approval in your Codex config so tool calls are not gated on confirmation.
Invoke: activate_skill autogrind or "autogrind this project"
cp -r autogrind ~/.gemini/skills/autogrind
# Or use the universal path: ~/.agents/skills/autogrind
Gemini CLI discovers skills automatically from ~/.gemini/skills/ — no GEMINI.md entry required. For local development, use gemini skills link to symlink.
Invoke: gemini "autogrind this project, don't stop until I say so"
cp -r autogrind ~/.agents/skills/autogrind
# Or: ~/.claude/skills/autogrind (OpenCode checks both)
OpenCode discovers skills automatically — no AGENTS.md entry required.
Invoke: opencode "autogrind this project, keep going until I say stop"
cp -r autogrind ~/.cursor/skills/autogrind
# Or use the universal path: ~/.agents/skills/autogrind
Enable auto-run for terminal commands in Cursor settings.
Invoke: "Keep working on this project autonomously. Don't stop."
# Preferred path
cp -r autogrind ~/.codeium/windsurf/skills/autogrind
# Or universal path
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "autogrind this project, don't stop"
# Preferred path
cp -r autogrind ~/.roo/skills/autogrind
# Or universal path
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "Keep working, don't stop"
# Preferred path
cp -r autogrind ~/.cline/skills/autogrind
# Or universal path
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "autogrind this project, keep going"
# Preferred path
cp -r autogrind ~/.trae/skills/autogrind
# Or universal path
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "autogrind this, don't stop" or /autogrind
cp -r autogrind ~/.config/agents/skills/autogrind
# Or project-level
cp -r autogrind .kimi/skills/autogrind
Invoke: /skill:autogrind or "keep working, don't stop"
# Preferred paths
cp -r autogrind ~/.copilot/skills/autogrind
# Or universal path
cp -r autogrind ~/.agents/skills/autogrind
Pair with a .github/copilot-instructions.md file to give Copilot project context.
Invoke: "autogrind mode — keep working autonomously" or /autogrind
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "autogrind this project, keep going"
# Preferred path
cp -r autogrind ~/.config/agents/skills/autogrind
# Or universal path
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "autogrind this, don't stop"
cp -r autogrind ~/.agents/skills/autogrind
All support the agentskills.io universal path. Install once, invoke directly.
Invoke: "Keep working on this project. Don't stop." or "autogrind"
cp -r autogrind ~/.agents/skills/autogrind
Invoke: "autogrind this, keep going"
Paste this into any agent chat:
Please update the AutoGrind skill to the latest version from https://github.com/ttttonyhe/autogrind-skills.
# If installed as symlink — no action needed, repo changes are live immediately.
# If installed as copy, re-run the install command:
cp -r autogrind ~/.claude/skills/autogrind # Claude Code
cp -r autogrind ~/.agents/skills/autogrind # Universal / Codex / Gemini / OpenCode / Cursor
flowchart TD
INIT["INIT (once)\nDetect guidance files\nExtract goals and conventions"]
OV["1. OVERVIEW\nAssess project state"]
UN["2. UNDERSTAND\nReview relevant work and history"]
PL["3. PLAN\nPrioritized tasks + frontier scan"]
WK["4. WORK\nExecute, validate, persist"]
RF["5. REFLECT\nGrounded signals + heuristics"]
PA["PAUSE 60s\nAnnounce, wait, continue"]
ST{"Explicit stop\nsignal?"}
STOP(["STOP"])
NEVER["NEVER stop\non your own"]
INIT --> OV --> UN --> PL --> WK --> RF --> PA --> ST
ST -->|yes| STOP
ST -->|no, always| OV
ST -.->|tempted to stop| NEVER
Every Reflect phase: checks verifiable signals first (test results, metrics, build status), evaluates core deliverable progress, scans quality dimensions (coverage, error handling, docs, performance, UX, observability, security), detects stuck loops and shifts focus, and extracts a transferable heuristic for the next cycle. There is always a weakest dimension.
After each cycle, AutoGrind pauses 60 seconds so you can interrupt. If you do nothing, it continues automatically.
When does it stop? What if my project is already complete?
AutoGrind stops only when you explicitly tell it to: "stop", "halt", "pause", "that's enough", or any clear termination request. It never stops on its own.
If your project feels done, AutoGrind will find the next improvement: coverage gaps, missing documentation, performance wins, edge cases, polish. The Reflect phase evaluates against a checklist of quality dimensions and always surfaces something. Say "stop" when you are satisfied.
Will it run destructive commands? Will I wake up to a broken system?
AutoGrind prioritizes reversible, tracked changes. Every code change gets committed to git, so you have a full undo trail. It does not intentionally run destructive operations (rm -rf, force push, DROP TABLE) as part of its workflow.
That said, AutoGrind runs code, edits files, and commits changes autonomously. Recommended safeguards:
git log before deploying anythingWill context compaction break AutoGrind?
No. Each cycle begins with an Overview phase that re-reads project state from scratch: git history, test output, file structure, open issues. AutoGrind does not depend on remembering previous cycles. Long sessions with multiple context compactions work fine.
Go to bed. Wake up to finished work.
You: autogrind this, i'm going to bed
Agent: [starts grinding]
cycle 1 - fixed broken import, added 12 tests
cycle 2 - documented all exported functions
cycle 3 - reduced DB query count by 40%
cycle 4 - added input validation, edge case tests
...
You: [8 hours later] stop
ML / data science - point it at a training script. It runs experiments, inspects metrics, adjusts hyperparameters, re-runs, and iterates. Come back to a full experiment trail and an improved model.
Academic research - grind through a literature review, fill methodology gaps, expand weak sections, cross-check citations. Each cycle improves the manuscript.
Codebase cleanup - point it at a messy repo. It fixes linting, improves coverage, fills doc gaps, and refactors the worst offenders, in priority order, with meaningful commits.
Design iteration - work through a revision backlog: consistency checks, accessibility improvements, copy edits, spacing fixes. Any workflow where "keep improving until told to stop" is the right mode.
AutoGrind commits after each logical change, with a meaningful message. When you return, git log tells the full story.
$ git log --oneline
f3a1b2c Reduce N+1 queries in UserRepository.findByOrg()
e8