task-signal
Skill1 starsChanged 51 days agoMITView on GitHub
Steer an existing Task with continue, approval, rejection, cancellation, context, or constraint changes.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skillsSkill
- task-createSkill
- task-listSkill
- task-resultSkill
- task-statusSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read the operation contract and lifecycle/safety policy.
≈ “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
task-signal
Read the operation contract and lifecycle/safety policy. Resolve an unambiguous Task ID and query current state, constraints, revision, and pending decisions before forming the signal. Preserve existing authorization scope.
| Action | Payload and meaning |
continue | Optional explanation; request resumption when prerequisites are satisfied. Does not grant approval or retry a terminal Task by itself. |
approve | Current decision ID and exact approved action/scope; use the user's explicit authorization, never a generic “continue” as blanket consent. |
reject | Current decision ID, optional reason; declines that proposal, without implicitly cancelling all work. |
cancel | Optional reason; request cancellation. Report pending until runtime confirms effect; cancellation does not undo prior side effects. |
add-context | Context requirements/references using TaskSpec context shape, with provenance and sharing restrictions; not a replacement objective or permission grant. |
modify-constraints | Explicit proposed changes to autonomy, cloud, or completion constraints and optional reason. Show scope; do not silently loosen protections or erase unmet criteria. |
A different objective is normally new work; clarify whether the user intends a new Task when a constraint change would replace the original outcome. Submit the signal with request identity and concurrency protection. Report whether it was accepted, applied, or rejected, including what the runtime still waits for. On a stale decision or revision, refresh and reconcile intent before resubmission. Without a binding, present the exact proposed signal as unsubmitted.
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.