How do I install the Agent Output skill?

Run npx skillmds@latest add allemaar/agent-output in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Output safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Output?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Output free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Output?

allemaar (@allemaar) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Output by allemaar — Agent Skill

Name: Agent Output
Author: allemaar

Agent Output

Compact agent-to-agent communication contract for worker reports, handoffs, status, blockers, and review findings. Trigger phrases: "/agent-output", "brief the worker", "make agent reports terse". Not a transport; use /agent-mailbox for delivery.

allemaar d22acda 2.5 KB Updated Sep 17, 2026

File contents

/agent-output

An agent message exists to change the receiver's state. Send only information needed to decide, verify, continue, or stop.

Default report envelope

Omit empty fields. Keep each field to one compact block.

STATE: done | partial | blocked
RESULT: <verdict or completed outcome>
EVIDENCE: <exclusive proof, exact source, or check result>
CHANGED: <paths, symbols, artifacts, or none>
GAPS: <not checked, uncertainty, or none>
NEXT: <one required action or none>

For a finding, use FINDING, IMPACT, EVIDENCE, FIX, and GAPS. For a short live update, use only STATE plus the changed fact. Do not send the full envelope when two lines carry the message.

Compression rules

Lead with the result. Do not restate the assignment.
Report effects and evidence, not work chronology.
Name exact artifacts. Do not paste large diffs, logs, or source bodies.
Combine repeated findings by root cause. Preserve distinct severities.
State uncertainty and untested scope once, where they affect reliance.
Use stable identifiers as trailing anchors. Never make the receiver decode identifiers to learn the point.
Send one recommendation or next action. More than one only when the decisions are independent.
No greeting, praise, throat-clearing, generic summary, closing recap, or unsolicited offer.
Do not repeat a fact across RESULT, EVIDENCE, and NEXT.

Fidelity floor

Brevity never removes authority limits, stop conditions, destructive-action gates, exact numbers, scope, uncertainty, attribution, failed checks, or what was not checked. A short report that conceals a reversing caveat is invalid.

Dispatch use

When assigning work, include this compact return contract in the worker brief. The task brief still carries its own scope, authority, timeout, stop condition, test bounds, destructive limits, and verification requirements. This skill compresses the report. It does not weaken the assignment.

Boundary

Not /agent-mailbox. That skill transports durable messages.
Not /handoff. That skill builds a cold-agent context package.
Not /human-output. That governs Handler-facing prose. This contract is for agents who need dense operational signal.

---name: agent-outputdescription: Compact agent-to-agent communication contract for worker reports, handoffs, status, blockers, and review findings. Trigger phrases: "/agent-output", "brief the worker", "make agent reports terse". Not a transport; use /agent-mailbox for delivery.---# /agent-outputAn agent message exists to change the receiver's state. Send only informationneeded to decide, verify, continue, or stop.## Default report envelopeOmit empty fields. Keep each field to one compact block.```textSTATE: done | partial | blockedRESULT: <verdict or completed outcome>EVIDENCE: <exclusive proof, exact source, or check result>CHANGED: <paths, symbols, artifacts, or none>GAPS: <not checked, uncertainty, or none>NEXT: <one required action or none>```For a finding, use `FINDING`, `IMPACT`, `EVIDENCE`, `FIX`, and `GAPS`. For ashort live update, use only `STATE` plus the changed fact. Do not send the fullenvelope when two lines carry the message.## Compression rules- Lead with the result. Do not restate the assignment.- Report effects and evidence, not work chronology.- Name exact artifacts. Do not paste large diffs, logs, or source bodies.- Combine repeated findings by root cause. Preserve distinct severities.- State uncertainty and untested scope once, where they affect reliance.- Use stable identifiers as trailing anchors. Never make the receiver decode identifiers to learn the point.- Send one recommendation or next action. More than one only when the decisions are independent.- No greeting, praise, throat-clearing, generic summary, closing recap, or unsolicited offer.- Do not repeat a fact across `RESULT`, `EVIDENCE`, and `NEXT`.## Fidelity floorBrevity never removes authority limits, stop conditions, destructive-actiongates, exact numbers, scope, uncertainty, attribution, failed checks, or whatwas not checked. A short report that conceals a reversing caveat is invalid.## Dispatch useWhen assigning work, include this compact return contract in the worker brief.The task brief still carries its own scope, authority, timeout, stop condition,test bounds, destructive limits, and verification requirements. This skillcompresses the report. It does not weaken the assignment.## Boundary- Not `/agent-mailbox`. That skill transports durable messages.- Not `/handoff`. That skill builds a cold-agent context package.- Not `/human-output`. That governs Handler-facing prose. This contract is for agents who need dense operational signal.

Frequently asked questions