create-loop
Skill1.5k starsChanged 6 days agoApache-2.0View on GitHub
Create a recurring Cloudroom Loop that starts an agent to check one thing, archives its thread when all is fine, and reports only when something needs the user. Use for "create loop", "create-loop", "create automation", or any "every N hours, have an agent check X" request.
- Reads credentials
1 other project uses a version of this.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- davidondrej/cloudroom-coreword for word, first seen Nov 1, 2026
Who's talking about davidondrej/cloudroom
- sudosubin/agents.nix“agent-skills.github.davidondrej.cloudroom: 03ddb1c → 112f097”GitHub · Nov 10, 2026
- sudosubin/agents.nix“agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-08 → 0-unstable-2026-11-10”GitHub · Nov 10, 2026
- sudosubin/agents.nix“agent-skills.github.davidondrej.cloudroom: 99252ed → 2d0f828”GitHub · Nov 9, 2026
- sudosubin/agents.nix“agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-07 → 0-unstable-2026-11-08”GitHub · Nov 8, 2026
- Ceoloo/aion-forge“Forge future UX — Safe code review, private previews and governed session transfer”GitHub · Nov 7, 2026
The biggest 5 of 25 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 25
Talked about on GitHub (25 times).
On GitHub · 25
- Nov 10, 2026agent-skills.github.davidondrej.cloudroom: 03ddb1c → 112f097 — sudosubin/agents.nix0 reactions
- Nov 10, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-08 → 0-unstable-2026-11-10 — sudosubin/agents.nix0 reactions
- Nov 9, 2026agent-skills.github.davidondrej.cloudroom: 99252ed → 2d0f828 — sudosubin/agents.nix0 reactions
- Nov 8, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-07 → 0-unstable-2026-11-08 — sudosubin/agents.nix0 reactions
- Nov 7, 2026Forge future UX — Safe code review, private previews and governed session transfer — Ceoloo/aion-forge0 reactions
20 more on GitHub
- Nov 7, 2026Forge v0.4 — Durable coding session lifecycle, queue and isolated Git workspaces — Ceoloo/aion-forge0 reactions
- Nov 7, 2026Forge Control Room v0.4 — Runtime-backed read-only session and workspace dashboard — Ceoloo/aion-forge0 reactions
- Nov 7, 2026agent-skills.github.davidondrej.cloudroom: e735f22 → becdfa7 — sudosubin/agents.nix0 reactions
- Nov 7, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-06 → 0-unstable-2026-11-07 — sudosubin/agents.nix0 reactions
- Nov 6, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-05 → 0-unstable-2026-11-06 — sudosubin/agents.nix0 reactions
- Nov 5, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-04 → 0-unstable-2026-11-05 — sudosubin/agents.nix0 reactions
- Nov 4, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-03 → 0-unstable-2026-11-04 — sudosubin/agents.nix0 reactions
- Nov 3, 2026Onde roda e ajudantes remotos (D235/D238) — gavasques/my-dexter-bot0 reactions
- Nov 3, 2026agent-skills.github.davidondrej.cloudroom: 0-unstable-2026-11-02 → 0-unstable-2026-11-03 — sudosubin/agents.nix0 reactions
- Nov 2, 2026agent-skills.github.davidondrej.cloudroom: 0.1.92 → 0-unstable-2026-11-02 — sudosubin/agents.nix0 reactions
- Nov 2, 2026execution model: Cloudroom options — what each feature would look like here (no adoption decision) — talos-hq/hermes-slim0 reactions
- Nov 2, 2026agent-skills.github.davidondrej.cloudroom: 0.1.91 → 0.1.92 — sudosubin/agents.nix0 reactions
- Nov 1, 2026agent-skills.github.davidondrej.cloudroom: 0.1.90 → 0.1.91 — sudosubin/agents.nix0 reactions
- Nov 1, 2026agent-skills.github.davidondrej.cloudroom: 0.1.89 → 0.1.90 — sudosubin/agents.nix0 reactions
- Oct 31, 2026agent-skills.github.davidondrej.cloudroom: 0.1.88 → 0.1.89 — sudosubin/agents.nix0 reactions
- Oct 31, 2026agent-skills.github.davidondrej.cloudroom: 0.1.87 → 0.1.88 — sudosubin/agents.nix0 reactions
- Oct 30, 2026agent-skills.github.davidondrej.cloudroom: 0.1.86 → 0.1.87 — sudosubin/agents.nix0 reactions
- Oct 30, 2026agent-skills.github.davidondrej.cloudroom: 0.1.85 → 0.1.86 — sudosubin/agents.nix0 reactions
- Oct 29, 2026agent-skills.github.davidondrej.cloudroom: 0.1.83 → 0.1.85 — sudosubin/agents.nix0 reactions
- Oct 29, 2026agent-skills.github.davidondrej.cloudroom: init at 0.1.83 — sudosubin/agents.nix0 reactions
Other versions1 project uses a version of this.
Word for word · 1
- davidondrej/cloudroom-core★ 1.5k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adr-verbatimSkill
- browser-harnessSkill
- decisionsSkill
- file-treeSkill
- risky-changesSkill
- self-archiveSkill
- setup-helpSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 4 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Ask only when the job itself is unclear.
- Very specific: line 15
Local threads: read the automations skill.
- Very specific: line 16
Cloud threads: run room-cli loop --help. Then read the room-cli skill.
- Very specific: line 22
Schedule: every 4 hours in the user's timezone: --cron "0 */4 * * *" --timezone <IANA zone>.
- Distinctive: line 28
Access: read only. No edits, commits, or pushes until the user approves a fix.
- Distinctive: line 31
Finish: all fine → 1-2 lines, then the thread archives itself.
- Very specific: line 38
Create it: Write the prompt to /tmp/<name>-prompt.txt, then:
- Very specific: line 58
Check that runs and last_run_at went up.
- Very specific: line 59
Check that last_error is empty.
- Distinctive: line 61
Ask the user to confirm its title and verdict in the app.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create loop
The user describes the job in a sentence. Fill in everything else from the defaults. Anything the user says overrides a default. Ask only when the job itself is unclear.
For flags, Cloud loops, and scripts:
- Local threads: read the
automationsskill. - Cloud threads: run
room-cli loop --help. Then read theroom-cliskill. Cloud steps differ: see "In a Cloud thread" below.
Defaults
- Schedule: every 4 hours in the user's timezone:
--cron "0 */4 * * *" --timezone <IANA zone>. - Agent: the same harness, model, and effort as this thread.
Locally, read them with
room-cli thread show --self --json. Cloud loops use them by default. - Where: a Local loop in the project's main checkout (first line of
git worktree list). No new worktrees. Use a Cloud loop when it must run with the user's computer off, and always from a Cloud thread. - One thread per run: every run is its own top-level thread. Never point a loop at one manager thread that re-prompts and spawns sub-agents: the runs pile up nested under it. Local loops and Cloud
--cronloops already start a fresh thread per run, so don't add--same-thread. A script that starts threads itself spawns them top-level: no--parent-selflocally,--top-levelin a Cloud thread, never--shared-sandbox. - Access: read only. No edits, commits, or pushes until the user approves a fix.
- Secrets: a Cloud loop gets only the API keys its job needs:
--secrets KEY,.envor--secrets none. - Safety: include the safety sentence below verbatim in every Local or Cloud loop prompt, including prompts embedded in scripts.
- Finish: all fine → 1-2 lines, then the thread archives itself. Something matters → a short verdict, thread left open for the user's Review tab.
- No repeats: skip issues already reported in open threads with the same title.
Steps
- Read the area first. Find the real files, docs, and skills the job touches. The loop's agent starts cold, so put concrete paths in its prompt.
- Write a short prompt from the template below. Simple and short beats thorough: a few lines, at most about 15, in calm, plain words. No long checklists, nothing adversarial. One job per loop. If the loop may push, delete, or flag a serious security issue, have it ask a subagent on another model to check first, in a few lines, like: "Branch X removes Y. Check it won't break anything. Only flag serious issues, not nitpicks. End with SHIP or HOLD: reason."
Create it. Write the prompt to
/tmp/<name>-prompt.txt, then:room-cli loop create --project "$ROOM_PROJECT_ID" --name "<Name> (every 4 hours)" \ --cron "0 */4 * * *" --timezone <zone> \ --provider <id> --model '<model>' --reasoning <level> \ --environment "<main checkout>" --prompt "$(cat /tmp/<name>-prompt.txt)" --json- Test it once. In a Cloud thread, see "In a Cloud thread" below.
Locally:
room-cli loop run ID --project "$ROOM_PROJECT_ID", thenroom-cli loop runs ID --project "$ROOM_PROJECT_ID" --limit 1 --jsongives its thread. Confirm it started and renamed itself. - Tell the user the loop's name, schedule, and test thread, plus anything surprising from step 1.
In a Cloud thread
- Drop
--projectand--environment. Cloud uses this thread's project. room-cli loop run IDonly makes the loop due.- Within a minute or two, find the loop's ID in
room-cli loop list. - Check that
runsandlast_run_atwent up. Check thatlast_erroris empty. - Cloud can't see the run's thread or output.
- Ask the user to confirm its title and verdict in the app.
Prompt template
<Name>. Read only: do not edit, commit, or push anything.
Never test destructive edge cases on live services; mock the API and reject missing or empty IDs before delete requests.
1. Rename this thread: `room-cli thread update --self --title "<Name> · $(date '+%b-%d %H:%M')"`.
2. Read: <concrete files and docs>.
3. Check: <what to look for, in plain words>.
4. Skip issues already reported in open threads titled "<Name>".
Finish:
- Nothing major: write 1-2 lines on what you checked, then run `room-cli thread archive --self --json`.
- Something worth fixing (<what counts as major for this job>): don't archive. Explain the single most important issue in 2-3 short, plain sentences, then one sentence on the safe fix. Then wait.Keep paid calls cheap
For jobs that pay per item (scrapes, search, paid APIs):
- Fetch only what's new. Save the last run time in a file and fetch only items after it.
- Keep a pool. Save good candidates for later runs instead of re-fetching the whole window.
- Skip hours nobody reads, e.g.
0 8-22/3 * * *.
Gotchas
- Pass
--projecton every Local loop command. - Threads a loop starts cannot create loops.
- Quote models with brackets:
'claude-opus-5-5[1m]'.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

