agentsclimarketplace

Waa agent delegation

Skill clearlove7818/waa-agent-delegation

Cross-platform Agent Skill for safe subagent selection, task packets, permissions, handoff, and verification.

Install
npx -y skills add clearlove7818/waa-agent-delegation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Govern an actual agent delegation only after the primary agent has decided to create or invoke a subagent. Use to choose exactly one EXECUTION_SUBAGENT, TASK_SPECIALIST_SUBAGENT, or explicitly authorized NAMED_AGENT; check capability, platform, permission, and external-effect boundaries; build a risk-sized TASK-006 packet; define handshake, failure, delivery, and handoff; and support primary-agent verification. Exclude complexity alone, delegation discussion, simple direct work, multi-agent demonstrations, unauthorized named-agent activation, permission expansion, and responsibility transfer.

SKILL.md

4.7 KB, 835 tokens by cl100k_base, as published. Nobody here has run it

Agent Delegation

Govern an already-chosen delegation without taking direction, extra authority, named-agent activation rights, or final responsibility.

<FAILURE-LABEL-CONTRACT>

Before execution, put one exact root-cause label on the first task-status line:

  • BLOCKED: critical task input is missing or the contract conflicts.
  • MISSING_CAPABILITY: a required capability is absent, incompatible, or unreliable.
  • CAPABILITY_OUT_OF_SCOPE: the capability exists but Rules or current task authorization excludes it.
  • PLATFORM_PERMISSION_BLOCKED: platform policy, sandboxing, or approval prevents the action.

Preserve these labels verbatim. If a required handshake stops, add Handshake: BLOCKED after the root-cause label. Delivery states apply only after execution starts.

</FAILURE-LABEL-CONTRACT>

Run the delegation loop

  1. Confirm real delegation is already chosen and useful for independent work, professional judgment, parallel benefit, or independent verification; otherwise do not dispatch.
  2. Choose exactly one EXECUTION_SUBAGENT, TASK_SPECIALIST_SUBAGENT, or authorized NAMED_AGENT. Visibility, availability, recommendation, or fit never authorizes a named Agent.
  3. Check capability fitness, platform compatibility, Rules, task authorization, platform permission, prohibitions, exceptions, and external effects.
  4. Build one risk-sized TASK-006 packet with task_packet_version, task_id, assembly_type, artifact_id, artifact_version, and one owner; vary only the depth of its nine information classes. Read references/protocol.md.
  5. Load only the active map: Codex, Claude Code, or Agy. Read platform compatibility when certainty matters.
  6. Apply the required handshake, dispatch through the current native interface, and preserve the packet boundary.
  7. Reconcile identity and ownership, verify returned evidence, and integrate only what it supports.

Apply executor rules

  • EXECUTION_SUBAGENT: use for bounded work following clear rules. Low-risk, reversible, unambiguous work with no external effect may skip the handshake; otherwise require ACCEPTED / BLOCKED.
  • TASK_SPECIALIST_SUBAGENT: use for non-mechanical professional judgment. Embed the eight-part temporary specialist_contract, always require ACCEPTED / BLOCKED, and create no persistent personality or tracking/promotion signal.
  • NAMED_AGENT: use only after the user selected it, or authorized the primary agent to choose and the choice was recorded. Always require ACCEPTED / BLOCKED and confirmation of that authorization basis.

ACCEPTED confirms understanding of the packet version, objective, evidence duty, standard, capability conditions, permissions, prohibitions, and return contract. It proves neither expertise, authority, execution, verification, nor success.

Preserve identity, ownership, and authority

Every packet has exactly one uppercase assembly_type and all six identity fields. The packet, required acceptance record, and result must preserve them; reject mismatches.

owner solely owns the current artifact version. The primary agent remains responsible for delegation, reception, verification, coordination, synthesis, user communication, and the integrated outcome without automatically owning each delegated version.

Every action must pass all three gates: Rules allow it, the packet authorizes it, and the platform permits it. Never switch capability or execution paths to bypass a gate.

Return and evaluate deliberately

After execution begins, return exactly one delivery state:

  • DONE: the minimum deliverable is complete and evidenced.
  • PARTIAL: disclose completed and unfinished work, impact, evidence, unknowns, and next handoff.
  • FAILED: the minimum deliverable was not reached; preserve cause, attempted scope, and evidence.

Independent evaluation is optional and separate. Connect it only when authorized and useful; never auto-start evaluation or a Loop. Subagent output remains evidence until the primary agent verifies and integrates it.

What ships with it: 13 files

107.4 KB alongside SKILL.md

agents/

evals/

Keep looking

Skills are one crate of 326,970. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.