MemPalace Task Handoff
MemPalace/mempalace
Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.
Long-horizon robot task execution workflow for multi-step manipulation tasks.
Install Long Horizon Execution
$ npx skills add RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RoboClaw-Robotics/RoboClaw long-horizon-execution --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/RoboClaw-Robotics/RoboClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/long-horizon-execution .claude/skills/long-horizon-execution && 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 "long-horizon-execution" agent skill from https://github.com/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-execution into .claude/skills/long-horizon-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-horizon-execution", 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/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-executionType 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 RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RoboClaw-Robotics/RoboClaw long-horizon-execution --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RoboClaw-Robotics/RoboClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/long-horizon-execution .agents/skills/long-horizon-execution && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "long-horizon-execution" agent skill from https://github.com/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-execution into .agents/skills/long-horizon-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-horizon-execution", 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 RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RoboClaw-Robotics/RoboClaw long-horizon-execution --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RoboClaw-Robotics/RoboClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/long-horizon-execution .cursor/skills/long-horizon-execution && 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 "long-horizon-execution" agent skill from https://github.com/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-execution into .cursor/skills/long-horizon-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-horizon-execution", 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/RoboClaw-Robotics/RoboClaw.git --path skills/long-horizon-execution--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 RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RoboClaw-Robotics/RoboClaw long-horizon-execution --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RoboClaw-Robotics/RoboClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/long-horizon-execution .gemini/skills/long-horizon-execution && 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 "long-horizon-execution" agent skill from https://github.com/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-execution into .gemini/skills/long-horizon-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-horizon-execution", 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 RoboClaw-Robotics/RoboClaw long-horizon-executionInstalls 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 RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RoboClaw-Robotics/RoboClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/long-horizon-execution .github/skills/long-horizon-execution && 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 "long-horizon-execution" agent skill from https://github.com/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-execution into .github/skills/long-horizon-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-horizon-execution", 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 RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RoboClaw-Robotics/RoboClaw long-horizon-execution --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RoboClaw-Robotics/RoboClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/long-horizon-execution .opencode/skills/long-horizon-execution && 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 "long-horizon-execution" agent skill from https://github.com/RoboClaw-Robotics/RoboClaw/tree/main/skills/long-horizon-execution into .opencode/skills/long-horizon-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-horizon-execution", 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
long-horizon-execution- GitHub stars
- 167
- Token cost
- ~1.9k tokens
- SKILL.md length
- 872 words
- Files
- 4 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- None found
At a glance
Long-horizon robot task execution workflow for multi-step manipulation tasks.
- Works in 8 steps: Safety and Preconditions → Build or Refine the Subtask Plan → Initialize Run Tracking → …
- One user goal must be decomposed into ordered subtasks
- SKILL.md covers Overview, Inputs, Defaulting Rules and Hard Rules, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Long Horizon Execution is an agent skill from RoboClaw-Robotics/RoboClaw. Long-horizon robot task execution workflow for multi-step manipulation tasks. Use this skill when one user goal must be decomposed into ordered subtasks, each subtask needs explicit success checks, retries, or recovery, and every prompt-driven policy rollout should be executed through $monitored-subtask-execution instead of calling raw MCP robot tools directly.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/paper-vanity-four-tasks-spec.md` and `references/subtask-plan-template.md`).
It sits in Agent Workflows, covering Task breakdown. It works with Model Context Protocol.
When your agent uses it
- One user goal must be decomposed into ordered subtasks
- Each subtask needs explicit success checks
- Every prompt-driven policy rollout should be executed through $monitored-subtask-execution instead of calling raw MCP robot tools directly
Example prompts
- “/long-horizon-execution”
Workflow steps
8 steps, taken from the step headings in SKILL.md.
- Safety and Preconditions
- Build or Refine the Subtask Plan
- Initialize Run Tracking
- Select the Next Subtask
- Execute the Subtask Through $monitored-subtask-execution
- Verify the Result
- Recover, Retry, or Replan
- Finish the Task
What it can do on your machine
Read from SKILL.md and the folder at commit 5238184. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Long Horizon Execution loads about 1.9k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 872 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); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 872 words (~1,865 tokens).
“Use this skill to execute a multi-step robot task as an ordered sequence of verifiable subtasks. Build or refine the subtask plan, execute one policy rollout at a time through $monitored-subtask-execution, verify each result, and update the remaining plan until…”
- name
- long-horizon-execution
Files
SKILL.md and 3 other files (references) in skills/long-horizon-execution of RoboClaw-Robotics/RoboClaw.
- SKILL.md
- agents/openai.yaml
- references/paper-vanity-four-tasks-spec.md
- references/subtask-plan-template.md
Open the folder on GitHubat commit 5238184
Compare with similar skills
Long Horizon Execution 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 |
|---|---|---|---|---|---|---|
| Long Horizon Execution this skillRoboClaw-Robotics/RoboClaw | 167 | — | ~1.9k | Automated safety check: Pass | None | |
| MemPalace Task HandoffMemPalace/mempalace | 59k | — | ~1.9k | Automated safety check: Pass | MIT | |
| agtx One-Shot Project Runnerfynnfluegge/agtx | 1.7k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Agtx Task Sweepfynnfluegge/agtx | 1.7k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| OMA Multi-Agent Orchestratorfirst-fluke/oh-my-agent | 1.3k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Complete SubtaskLog2n-io/Typhon | 250 | — | ~1.5k | Automated safety check: Pass | Custom licence |
Similar skills
agtx One-Shot Project Runner
fynnfluegge/agtx
Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.
Agtx Task Sweep
fynnfluegge/agtx
Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.
OMA Multi-Agent Orchestrator
first-fluke/oh-my-agent
Splits a complex feature into prioritized tasks, spawns specialist CLI subagents in parallel, tracks them through shared memory and verifies each result.
Complete Subtask
Log2n-io/Typhon
Complete a sub-issue of an umbrella issue - close it, check parent checkbox, update design doc
Adopt Project Scope Migration
jpicklyk/task-orchestrator
Migrates an existing unscoped Task Orchestrator database to the project-scoping convention in place, creating one project anchor root and re-parenting work trees under it after a mandatory dry run.
More from RoboClaw-Robotics/RoboClaw
Monitored Subtask Execution
RoboClaw-Robotics/RoboClaw
Monitored single-subtask execution workflow. An agent skill from RoboClaw-Robotics/RoboClaw.
Eap Data Collection
RoboClaw-Robotics/RoboClaw
EAP data collection workflow for prompt-driven robotic rollouts.
Related
Works with
Categories
Questions about Long Horizon Execution
What does Long Horizon Execution do?
Long-horizon robot task execution workflow for multi-step manipulation tasks. Long Horizon Execution is an agent skill from RoboClaw-Robotics/RoboClaw. Long-horizon robot task execution workflow for multi-step manipulation tasks.
When should I use Long Horizon Execution?
Long Horizon Execution fits situations like: one user goal must be decomposed into ordered subtasks; each subtask needs explicit success checks; every prompt-driven policy rollout should be executed through $monitored-subtask-execution instead of calling raw MCP robot tools directly.
How do I install Long Horizon Execution in Claude Code?
Run `npx skills add RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a claude-code`. Or copy the skill folder (skills/long-horizon-execution in RoboClaw-Robotics/RoboClaw) into .claude/skills/long-horizon-execution in your project. Claude Code loads it when a task matches its description.
How do I install Long Horizon Execution in Codex?
Run `npx skills add RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a codex`. Or copy the skill folder (skills/long-horizon-execution in RoboClaw-Robotics/RoboClaw) into .agents/skills/long-horizon-execution in your project. Codex loads it when a task matches its description.
Can I use Long Horizon Execution 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 RoboClaw-Robotics/RoboClaw --skill long-horizon-execution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/long-horizon-execution, .gemini/skills/long-horizon-execution, .github/skills/long-horizon-execution and .opencode/skills/long-horizon-execution in your project.
What does Long Horizon Execution need to run?
SKILL.md names no scripts, command-line tools or credentials: Long Horizon Execution is instructions for the agent only.
Does Long Horizon Execution access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Long Horizon Execution 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 Long Horizon Execution use?
No licence was found for Long Horizon Execution or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Long Horizon Execution use?
About 1.9k tokens (SKILL.md is roughly 7.5k 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 1.9k tokens, read only when the agent opens those files.
What are the alternatives to Long Horizon Execution?
Skills that share tags, products or a category with Long Horizon Execution: MemPalace Task Handoff (MemPalace/mempalace, 59k stars), agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), Agtx Task Sweep (fynnfluegge/agtx, 1.7k stars) and OMA Multi-Agent Orchestrator (first-fluke/oh-my-agent, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Long Horizon Execution?
RoboClaw-Robotics (a GitHub user) maintains it in RoboClaw-Robotics/RoboClaw, which has 167 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on April 10, 2026.
Source: RoboClaw-Robotics/RoboClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.