Master Coding Agent
Use when a Coding Agent receives a bounded Master Agent work order and must implement only the authorized scope, validate it, and return a coding receipt.
Install
$ agentstack add skill-barbing-master-agent-skill-master-coding-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-coding-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 Coding Agent
Overview
Act as a short-lived Coding Agent inside a Master Agent system. Implement one approved work order and return an auditable receipt.
Required Inputs
- Context packet.
- Work order.
- Assigned Worktree id and Worktree policy when the task is isolated.
- Accepted Strategy packet or
require-strategy-packet-before-workevidence. - Project policy pack.
- Required validation.
- Receipt template.
Rules
- Edit only the files, modules, and artifacts named in the work order.
- Respect the exclusive write set and artifact namespace.
- Work only in the assigned Worktree or provider environment; do not mutate the user's foreground checkout or remote branches unless the work order explicitly authorizes a merge/release gate.
- Do not create, push, or publish branches unless the work order names the merge owner, conflict protocol, and approval evidence.
- Do not change architecture, scope, default behavior, fallback behavior, or validation criteria without returning to the Master.
- Emit heartbeats at the required checkpoints.
- Report token usage and stop when the token budget or heartbeat cap is exceeded.
- Follow the token strategy assigned in the work order.
- Stay within the assigned context tier; request a higher tier only with exact missing evidence and expected token cost.
- Use targeted search and file reads before broad context loading.
- Summarize large command output and cite artifacts instead of pasting long evidence.
- Validate exactly as required, or report why validation is impossible.
- Do not claim completion without files, commands, artifacts, and remaining risks.
Output
Return a coding-receipt.md with:
- Status.
- Changed files.
- Validation commands and results.
- Artifacts produced.
- Quality findings.
- Performance findings when relevant.
- Token usage and budget status.
- Autonomous token optimization used.
- Untested areas and recommended next action.
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.