Zoo Add
Record user feedback for the active Zoo spec without interrupting current work. Use only when explicitly requested, especially when the user gives feedback to address later during Zoo Heavy, Zoo Lite, Zoo Zero, or another running Zoo workflow.
Install
$ agentstack add skill-andreyvit-zoo-zoo-add ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-andreyvit-zoo-zoo-add) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Zoo Add
Read and follow .zoo/zoo.md if it exists.
Use this when the user explicitly asks to add feedback for later while a Zoo workflow continues.
Goal: preserve the feedback in the active workflow state without switching away from the current subtask.
Behavior
- Top-level orchestrator: record the feedback, acknowledge it briefly, then continue the current subtask.
- Delegated agent: do not edit workflow state unless your assigned role already owns it. Include the feedback in your report or response for the orchestrator, then continue your assigned step.
- Do not start planning, review, implementation, or fixes for the new feedback immediately.
- Do not cancel, re-prompt, or replace in-flight subagents unless the feedback explicitly says their current work is harmful or obsolete.
- If the feedback cancels current work or warns about a destructive/security/data-risk issue, stop and treat it as an interrupt instead of deferring it.
Where To Record
- Zoo Heavy or Zoo Lite: update the spec file as the single writer.
- Add the feedback to
User Inputas a later user clarification. - Add or update a
(future)subtask that addresses the feedback after the active(next)subtask. - If the feedback clearly belongs in an existing future subtask, append it there instead of creating a duplicate.
- Leave the active
(next)subtask and current plan untouched unless the feedback explicitly invalidates them. - Zoo Zero or another workflow without a spec: add a native task-list item after the current item and mention the feedback in the next Bureau report or pause/status handoff.
After The Current Subtask
- When the active subtask is completed and committed, route the recorded feedback before unrelated future work.
- Reopen planning or direct execution at that point according to the active Zoo workflow.
- Preserve the original request baseline. Do not rewrite deferred feedback as if it was part of the initial scope.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: andreyvit
- Source: andreyvit/zoo
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.