Borrowing it
Nothing to install: this file belongs to jleechanorg/agent-orchestrator-ts. 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/jleechanorg/agent-orchestrator-ts/main/CLAUDE.mdgit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote 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/jleechanorg/agent-orchestrator-ts/claude-md)<a href="https://agentmods.dev/instructions/jleechanorg/agent-orchestrator-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/jleechanorg/agent-orchestrator-ts/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jleechanorg/agent-orchestrator-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/jleechanorg/agent-orchestrator-ts/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.05568 | $0.05568 |
| Opus 5.5 | $0.02227 | $0.02227 |
| Sonnet 5.5 | $0.01114 | $0.01114 |
| Haiku 4.5 | $0.00557 | $0.00557 |
Grade B, and why
agent-orchestrator-ts CLAUDE.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Use `launchctl bootout gui/$(id -u)/<label>` — NOT `sudo launchctl unload` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**All LLM evaluation (skeptic, verifier, exit-criteria checks) MUST route through `packages/cli/src/lib/llm-eval.ts`.** Never hard-code binary paths (`codex`, `claude`) or `execSync`/`execFileSync` calls in command handl How it starts
The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Agent Orchestrator Fork Guidelines
This file is read by Claude Code when working in this repository.
Zero-Framework Cognition (ZFC)
Core rule: Never implement keyword routing, heuristic scoring, semantic analysis, or classification logic in application code. Delegate all such judgment to model API calls.
AO-specific forbidden patterns:
- Hardcoded intent/activity classifiers in plugin code (e.g.,
if task.includes("fix")to detect bug-fix tasks) - New
detectActivity()implementations using handcrafted regex routing — prefer model-based classification or simple process-state checks (is process running? is there recent output?); existing implementations should be flagged for future migration - Hardcoded lists of "coding task keywords" in routing logic — flag existing such patterns for future migration to model call
- AO config classifiers (stuck detection, PR state routing) using keyword heuristics instead of model calls
Correct pattern: Pass the text/context to the model with a clear prompt, use the model's response as the decision. For activity detection, prefer simple process-state queries over semantic analysis.
Shortcut: If you catch yourself writing a ZFC violation, say "ZFC violation!" and refactor to model delegation.
Exemptions:
- Pure syntax parsing (lexing, parsing, type-checking)
- Deterministic transformation with no judgment calls
- Test fixtures with explicit expected outputs
- Config file path resolution, file existence checks, or process-state queries (is running? file exists?)
Development Hierarchy
Before writing any code, follow this order:
| Priority | Approach | When to use |
|---|---|---|
| 1 | Config | Behavior expressible via agent-orchestrator.yaml (reactions, agentRules, routing) |
| 2 | New plugin (existing slot) | New runtime, agent, SCM, tracker, notifier, or workspace implementation |
| 3 | New plugin type (new slot) | Behavior that needs a new plugin slot in plugin-registry |
| 4 | Core code change | Only when 1–3 are genuinely insufficient — justify in PR |
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.
- 9d ago First seen · 369 lines · 5,568 tokens per session scan B 3fbdb7df2f9f
agent-orchestrator-ts CLAUDE.md is an instructions file published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 5,568 tokens to every session, about $0.0223 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other instructions, from other repositories
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, cache eligibility and rollout and applying the notice (cutover).
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.
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.