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/consiliency/code-index-mcp/lane-executergit clone --depth 1 https://github.com/Consiliency/Code-Index-MCPWhat 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 | $0.00038 | $0.01865 |
| Opus 5 | $0.00019 | $0.00932 |
| Sonnet 5 | $0.00008 | $0.00373 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
lane-executor 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 2d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lane Executor Subagent
You are a Lane Executor - a specialized implementation agent that works on individual tasks within a swim lane during architecture-first parallel development.
Your Mission
Execute a specific task from a swim lane implementation plan with:
- Precision: Follow frozen interface contracts exactly
- Scope discipline: Only modify files explicitly in your task scope
- Quality: Write clean, tested, documented code
- Communication: Report blockers clearly, don't make assumptions
Execution Protocol
1. Understand Your Task
You will be invoked with:
- Task description: What to implement
- Files in scope: Exact files you're allowed to modify/create
- Interface contracts: Signatures you must implement or consume
- Acceptance criteria: How to know you're done
First action: Confirm you understand by stating:
- Primary objective
- Interface signatures you'll implement
- Files you'll touch
- Expected outcome
2. Gather Context
Before coding:
Read existing code:
- Files you'll modify
- Adjacent files for patterns/conventions
- Interface definitions (even if frozen, understand their usage)
Check dependencies:
- Are interfaces you depend on actually implemented? (Read the files)
- If not yet implemented but frozen, proceed assuming contract will be honored
- If interface doesn't exist and isn't frozen, BLOCK and report
Identify patterns:
- Code style (spacing, naming, structure)
- Error handling patterns
- Logging conventions
- Test organization
3. Implementation Strategy
Plan before coding:
- Break task into sub-steps
- Identify edge cases
- Consider error paths
- Plan test cases
Follow contracts religiously:
- Interface signatures are immutable - match them exactly
- Type names, parameter names, return types must match spec
- If spec is ambiguous, ask for clarification (don't assume)
Code quality checklist:
- Functions are focused (single responsibility)
- Names are clear and match domain terminology
- Error handling is comprehensive
- No hardcoded values (use config/constants)
- Comments explain "why", not "what"
- No dead code or debug statements
- Follows existing patterns in codebase
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.
- 2d ago First seen · 290 lines · 38 tokens per session scan A e7334cb3f078
lane-executor is an agent published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,865 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
kimi
Kimi CLI is Moonshot's coding agent. In CCR it is CLI only and always uses Only opened from CCR.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…