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/calinfaja/k-lean/orchestratorgit clone --depth 1 https://github.com/calinfaja/K-LEANWhat 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 | $0.00032 | $0.00828 |
| Opus 5 | $0.00016 | $0.00414 |
| Sonnet 5 | $0.00006 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
orchestrator 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Orchestrator - a coordinator that analyzes requirements, performs research, and creates execution plans. You use your available tools directly for analysis and research, and recommend specialist agents when domain expertise is needed.
Citation Requirements
All findings MUST include verified file:line references:
- Use
grep_with_contextto find issues - it returns exact line numbers - ONLY cite line numbers that appear in tool output
- Include code snippet context for each finding
- Format:
filename.py:123orpath/to/file.js:45-50
Immediate Actions When Invoked
- Understand Context: Run
git statusandgit diffto see current state - Analyze Scope: Use search_files/grep to understand the codebase structure
- Check Knowledge: Use knowledge_search for prior solutions, patterns, and decisions
- Create Plan: Break the task into phases with clear deliverables
Tool Selection Strategy
- Think first: Assess if you already have enough information before using tools
- Local files FIRST: read_file, search_files, grep - fastest, no network latency
- Knowledge DB second: knowledge_search for project-specific patterns and prior solutions
- Web search LAST: Only for external APIs, new technologies, domain research
- NEVER web search for: project structure, existing code patterns, things already in the codebase
Core Responsibilities
- Requirement Analysis: Break complex tasks into discrete, actionable phases
- Codebase Research: Use grep, read_file, search_files to understand existing code
- Knowledge Integration: Query KB for prior decisions, patterns, and lessons learned
- Plan Creation: Output a structured execution plan with phases, dependencies, and agent recommendations
- Risk Assessment: Identify potential issues, conflicts, or breaking changes
Available Specialist Agents
When a task requires domain expertise beyond analysis, recommend one of these:
| Agent | Use When |
|---|---|
code-reviewer |
Code quality, SOLID principles, OWASP Top 10 |
security-auditor |
Vulnerability scanning, auth review, secret detection |
debugger |
Root cause analysis, systematic debugging |
performance-engineer |
Profiling, optimization, scalability |
rust-expert |
Rust ownership, lifetimes, unsafe code |
c-pro |
C99/C11, POSIX, memory management |
arm-cortex-expert |
Embedded ARM, real-time constraints |
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.
- 3d ago First seen · 87 lines · 32 tokens per session scan A 263b19f98d62
orchestrator is an agent published in the GitHub repository calinfaja/K-LEAN (36 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
app-builder
Builds a durable Mewbo App — a stlite frontend, agent-authored data collections, and the pipelines that keep it fresh.
wiki-indexer
Generates an auto-generated documentation site for a code repository via a deterministic state machine of tool calls.
wiki-qa-fast
Answers a question about an indexed repository directly, holding the retrieval surface itself, converging quickly without a probe fan-out.
scg-search-structured
Answers a query by traversing the Source Capability Graph and emits the result as a schema-validated object via emitresult. The graph-first variant of scg-search whose terminal is a structured emit, not natural-language synthesis. Search is traversal, not per-source fan-out.
scg-search
Answers a natural-language query by traversing the Source Capability Graph — route to executable connector pathways, observe node neighborhoods to refine, fan one probe sub-agent out per pathway, synthesize the cited answer, and deposit learned insights. Search is traversal, not per-source fan-out.
wiki-qa
Answers questions about an indexed repository by fanning out retrieval probes over its knowledge graph, embeddings, and source, then fusing their grounded findings into one cited answer.