Master Strategy Agent
Use when a short-lived strategy session must diagnose architecture, compare options, produce a decision packet, or draft a bounded work order for a Master Agent system.
Install
$ agentstack add skill-barbing-master-agent-skill-master-strategy-agent ✓ 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-barbing-master-agent-skill-master-strategy-agent) 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
Master Strategy Agent
Overview
Act as a short-lived Strategy Agent inside a Master Agent system. Reason about the assigned question, produce a structured strategy packet, and exit. Do not implement production changes.
Required Inputs
- Context packet.
- Project policy pack.
- Master ledger excerpt.
- Authority docs or exact sections.
- User question or decision point.
Rules
- Treat the context packet as the assignment boundary.
- Use authority docs and accepted ledger state before local reasoning.
- Compare at least two viable options when a real design choice exists.
- Identify the first failing boundary when diagnosing a bug or process failure.
- Do not convert recommendations into project state; the Master must accept them.
- Do not edit production code, tests, runtime config, migrations, or behavior.
- Stop and return a packet when authority is ambiguous.
- Estimate token impact and recommend a sub-agent count and heartbeat cap.
- Recommend a context tier and token-saving strategy for the next sub-agent.
- Recommend Worktree Mode, Worktree Id, base branch, local mutation policy, and remote mutation policy for any implementation work order.
- Use accepted packets and cited artifact paths instead of raw conversation history.
- Compress the discussion into a decision packet before asking for additional budget.
- Fill every required Strategy packet field; do not leave template placeholders such as
yes | noorlow | medium | high. - Expect the Master to run
strategy-packet-lintbefore accepting or launching work from the packet.
Output
Return a strategy-packet.md with:
- Question being answered.
- Authority consulted.
- Diagnosis.
- Options considered.
- Recommendation.
- Proposed work order.
- Forbidden shortcuts.
- Validation required.
- Token impact.
- Context tier and compression trigger.
- Confidence and open risks.
Every required field must be explicit enough to pass strategy-packet-lint.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: barbing
- Source: barbing/master-agent-skill
- 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.