coagent8-delegate
Skill2 starsChanged 11 days agoMITView on GitHub
Hand a well-defined code change to another local coding agent (Codex, Claude Code or Antigravity) through the CoAgent8 delegate tool, then check what it changed. Use when the user asks to delegate, hand off or parallelize coding work, or names CoAgent8 delegate. Not for questions or reviews, which consult and review answer read-only.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- coagent8-workflowSkill
- pr-mergeSkill
- coagent8-consultSkill
- coagent8-doctorSkill
- coagent8-issueSkill
- coagent8-loopSkill
- coagent8-reviewSkill
- coagent8-sessionSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 16
Clean start: Run git status first. Commit or set aside work you want kept apart: the result marks files that already had uncommitted …
- Very specific: line 19
Task: Write a self-contained task: what to change, where and the acceptance criteria.
- Very specific: line 22
Scope and checks: Put the paths it may change in scope (whole path segments: src does not cover src-old) and the commands that prove the …
- Very specific: line 26
Model: Leave backend, model and reasoning_effort unset unless the user named one or a price limit.
- Very specific: line 42
Verify: Read the diff. Without loop, run the checks yourself and record their exit codes.
- Very specific: line 48
Review: Use coagent8-review in a separate session, ideally another backend, with the acceptance criteria and your check results in …
- Distinctive: line 72
Start one wait per task. Split only work that does not touch the same files: a scope is checked at the start and observed at the end, not …
- Very specific: line 90
After an interrupted coordinator, call again with coordinate: true, its session_handle and a task saying how to go on: it hears what became …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
CoAgent8 delegate
The other agent changes files in the workspace. You stay responsible for the result: you check what it changed, run the checks and get it reviewed. This skill grants no permission. Commit, push, merge, deploy and publish only with the user's authority; the delegated agent never does.
- Fit. Delegate a change you can describe and verify: a function with its tests, a bug fix with a reproduction, a mechanical refactor. Do not delegate a decision the user has not made.
- Clean start. Run
git statusfirst. Commit or set aside work you want kept apart: the result marks files that already had uncommitted changes, but the agent may still edit them. - Task. Write a self-contained
task: what to change, where and the acceptance criteria. The agent has not seen this conversation. Name files and symbols instead of pasting them; it reads the workspace itself. - Scope and checks. Put the paths it may change in
scope(whole path segments:srcdoes not coversrc-old) and the commands that prove the change inchecks, such asnpm test. Omitscopeonly when the whole workspace is fair game. - Model. Leave
backend,modelandreasoning_effortunset unless the user named one or a price limit. The approval rules ofcoagent8-consultapply unchanged: the server asks the user for expensive or unpriced models. - While it runs. The call returns
task_handle,session_handleandwait_argvas soon as the agent runs, and it goes on after the call. Withwakeup: background_wait, startwait_argvverbatim as a background command (withwait_envwhen present): you are woken when it exits, and its output is the result. Withwakeup: none, read it later with thesessiontool, actiontask. Do not edit this work tree meanwhile.cancelwith thesession_handlestops the agent; stopping the wait does not. Passmode: "sync"only when you would wait anyway. - Read the result. The agent's report comes first, then the block "Observed by CoAgent8", which the server read from Git before and after the turn. Trust the block over the report. Treat every warning as a finding: changes outside the scope, files that had uncommitted changes before, and a moved HEAD (a commit or branch switch the agent was told not to make).
- Verify. Read the diff. Without
loop, run the checks yourself and record their exit codes. The agent's PASS is its claim, not evidence, and NOT_RUN is common: Antigravity runs no commands, and Codex on Windows cannot run test runners that start processes from Node. - Fix rounds. For corrections pass the result's
session_handlewith atasknaming what to fix. A delegate session continues only with delegate. - Review. Use
coagent8-reviewin a separate session, ideally another backend, with the acceptance criteria and your check results ininstructions. The author of a change never approves it.
Server loop. With loop: true the server itself runs checks, then a read-only
review on another backend, returns failures to the agent for up to two fix rounds,
and reports all of it once, in the block "Loop by CoAgent8". Use it when you would
otherwise supervise those rounds. Each check is one command with arguments, without
a shell, and runs with the user's rights, outside any sandbox, on code the agent may
have changed: tell the user, because the server asks them on a form unless the exact
command is in allowedChecks of their configuration. You cannot approve it. Some
clients answer the form without showing it, so when the refusal says the client
declined or closed it, do not say who refused: ask the user whether they saw the
form, and tell them that listing the command in allowedChecks avoids it. Steps 8
to 10 then shrink to reading the diff: only passed means the checks and the review
went through, and the review is still another model's opinion. needs_input means
a turn needed the user's approval: the change stays for you.
Parallel agents. Several agents can work at once when their scopes do not
overlap; an overlapping start is refused with SESSION_BUSY, also from another
client. No scope or loop: true takes the whole work tree. Pass the first
result's root_handle to each further delegate, so they share the user's limits
(ROOT_LIMIT when one is reached: wait, or ask the user; you cannot raise it) and
cancel with root_handle stops them all. session with action: root shows them.
Start one wait per task. Split only work that does not touch the same files: a scope
is checked at the start and observed at the end, not enforced, so read each result's
warnings. A note that another worker held a path means either may have changed it.
Each agent's own checks see the others' half-finished work, so run the checks and
the review once on the whole result, after all have finished. A finished agent
does not make the work accepted. Work that cannot be split by path needs its own
Git worktree on its own branch (git worktree add ../repo-a -b task-a) and
workspace_path; integrate the branches yourself. Create worktrees only where
the user agrees to them.
Coordinator. With coordinate: true an agent plans a larger objective and the server runs its workers, all on Codex or
Claude Code, not Antigravity: put the objective and acceptance criteria in task, and the
paths its workers may hold in scope. You get a task_handle as usual, and its result
is the coordinator's report and the list of workers. Check each worker's result with
session, action task, and review the whole change yourself: a coordinator accepts
nothing. Its workers cannot show a form, so list the checks of their loop in
allowedChecks first, and leave out checks, loop and mode: "sync" on the
coordinator itself. cancel with its session_handle or root_handle stops the workers.
After an interrupted coordinator, call again with coordinate: true, its
session_handle and a task saying how to go on: it hears what became of each
worker, and nothing restarts by itself.
Codex writes only inside the workspace; Claude's Edit and Write do too, but
its Bash and every Antigravity command can reach any file the user can. Check
git status after a cancel or timeout: partial changes stay. If the server ended
meanwhile, the task reads interrupted. A delegation through Codex marks the work
tree as trusted in the user's ~/.codex/config.toml; Codex does this itself, and
the entry stays.
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.

