Borrowing it
Nothing to install: this file belongs to future-architect/uzomuzo-oss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/future-architect/uzomuzo-oss/main/.github/instructions/agent-orchestration.instructions.mdgit clone --depth 1 https://github.com/future-architect/uzomuzo-ossWrote 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/instructions/future-architect/uzomuzo-oss/agent-orchestration)<a href="https://agentmods.dev/instructions/future-architect/uzomuzo-oss/agent-orchestration"><img src="https://agentmods.dev/badge/instructions/future-architect/uzomuzo-oss/agent-orchestration.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 | $0.02187 | $0.02187 |
| Opus 5 | $0.01094 | $0.01094 |
| Sonnet 5 | $0.00437 | $0.00437 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
uzomuzo-oss agent-orchestration.instructions.md 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestration
Agent invocation
Agents are launched via the Task tool. The legacy Agent(...) API has been replaced with Task(subagent_type=..., prompt=...).
Task(subagent_type="<named>", prompt="...") # named subagent
Task(subagent_type="general-purpose", prompt="...") # generic agent + freeform prompt
general-purpose is not a named subagent_type with a pre-registered prompt template — it's a generic agent where the prompt you pass becomes the entire instruction. Use it for review focuses or open-ended investigations not covered by a named subagent (e.g., /review-until-clean Phase A's "Code Reuse" / "Code Quality" / "PR Hygiene" passes).
Available subagent types
| subagent_type | Kind | Purpose | When to Use | Isolation |
|---|---|---|---|---|
| planner | named | Implementation planning | Complex features, refactoring | — |
| architect | named | System design | Architectural decisions, package structure | — |
| code-reviewer | named | Code review | After writing code | — |
| refactor-cleaner | named | Dead code cleanup | Code maintenance | worktree |
| doc-updater | named | Documentation | Updating docs, godoc | worktree |
| deep-inspector | named | EOL batch evidence fetching | Deep Inspection orchestration | — |
| general-purpose | generic | Any focused review / investigation | Review focuses without a named subagent (e.g., Code Reuse / Quality / PR Hygiene), open-ended search | — |
Available Skills
| Skill | Command | When to Use |
|---|---|---|
| review-until-clean | /review-until-clean |
1-shot to merge-ready (local-only): Phase A (5-agent local review) → Phase B (push + self-driven Copilot re-review iteration) → Phase C (reply+resolve). Final pre-merge skill |
| deadcode | /deadcode [fix] [path] |
Quick dead code audit or interactive cleanup |
| batch-issues | /batch-issues [issue#s] [--dry-run] [--max-parallel N] |
Parallel issue processing with conflict-aware agent dispatch |
| diet-trial | /diet-trial <org/repo> [--tool trivy|syft] [--compare] |
Run diet on external OSS for testing, bug finding, and case study data |
| diet-fuzz | /diet-fuzz <languages|all> [--count N] [--tool trivy,syft,cdxgen] [--max-parallel N] |
Batch fuzz-test diet across many OSS projects for parser accuracy bugs |
| review-diff | /review-diff [BASE_REF | --cached] |
Pre-push diff review by the local Copilot CLI (gpt-5.6-sol, a separate-vendor LLM). Default base=origin/main; pre-empts a Phase B Copilot-bot round-trip. The same Copilot CLI is also wired into /review-until-clean Phase A as the always-spawned Reviewer 7. |
| plan-review | /plan-review [<plan-path>] |
Have the local Copilot CLI (gpt-5.6-sol) critique the latest plan-mode plan file (/home/node/.claude/plans/*.md) — a sanity check before ExitPlanMode. |
| plan-debate | /plan-debate [<plan-path>] |
Heavyweight /plan-review: gpt-5.6-sol reviews the plan, Claude ↔ gpt-5.6-sol debate up to 2 rounds, then the architect subagent rules neutrally (adopt / revise / reconsider). For high-rework-cost plans (billed in GitHub AI Credits, not Premium requests — see .github/prompts/plan-debate.prompt.md's Cost section; the old premium ~15-22 estimate used the legacy billing unit and is obsolete for gpt-5.6-sol); send trivial plans to /plan-review. |
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 · 118 lines · 2,187 tokens per session scan A 6a13c9c7b8ab
uzomuzo-oss agent-orchestration.instructions.md is an instructions file published in the GitHub repository future-architect/uzomuzo-oss (32 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,187 tokens to every session, about $0.0109 per session on Opus 5. 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 2026-09-01.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.