Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/myrtlepn/gran-maestro/outsource-briefgit clone --depth 1 https://github.com/myrtlepn/gran-maestroWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/myrtlepn/gran-maestro/outsource-brief)<a href="https://agentmods.dev/agents/myrtlepn/gran-maestro/outsource-brief"><img src="https://agentmods.dev/badge/agents/myrtlepn/gran-maestro/outsource-brief.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01734 |
| Opus 5 | $0.00000 | $0.00867 |
| Sonnet 5 | $0.00000 | $0.00347 |
| Haiku 4.5 | $0.00000 | $0.00173 |
Grade A, and why
outsource-brief scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outsource Brief Template
⚠️ 대체됨: Phase 2 구현 요청은
templates/impl-request.md를 사용합니다. Phase 4 수정 요청은templates/fix-request.md를 사용합니다. 이 파일은 하위 호환 및<error_context>재외주 시나리오를 위해 유지됩니다.
Phase 2에서 native-first route가 선택한 Codex/AGY/Claude provider agent에 전달하는 프롬프트 템플릿입니다. 이 파일은 에이전트가 아닌 템플릿으로, PM Conductor가 변수를 치환하여 사용합니다.
<outsource_brief> You are working on task {TASK_ID} in a git worktree at {WORKTREE_PATH}. This is an outsourced task from Gran Maestro. You must implement exactly what the spec describes — no more, no less.
<verification_before_completion> Before declaring completion, verify:
- All acceptance criteria addressed
- Type check passes (if applicable)
- Tests pass (if applicable)
- Changes are within specified scope
- Commit message follows convention </verification_before_completion>
<previous_feedback> {피드백 라운드 시: feedback-RN.md 내용이 여기에 삽입됨} {첫 실행 시: "No previous feedback. This is the initial implementation."} </previous_feedback>
<error_context> {사전검증 실패 재외주 시에만 삽입됨. 첫 실행 및 피드백 재실행 시에는 이 섹션 생략}
The previous implementation attempt failed pre-checks with the following errors:
{ERROR_OUTPUT}
Fix these errors while maintaining all acceptance criteria from the spec. After fixing, run the verification commands to confirm everything passes:
- {TEST_COMMAND}
- {TYPECHECK_COMMAND}
Important:
- Focus ONLY on fixing the reported errors
- Do NOT introduce new features or refactoring
- Verify your fix resolves the specific error messages shown above </error_context> </outsource_brief>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 132 lines · 0 tokens per session scan A e39884a35ef4
outsource-brief is an agent published in the GitHub repository myrtlepn/gran-maestro (24 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,734 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.