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 skills add KylinMountain/nano-claw --skill coding-routergit clone --depth 1 https://github.com/KylinMountain/nano-clawWrote 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/skills/kylinmountain/nano-claw/coding-router)<a href="https://agentmods.dev/skills/kylinmountain/nano-claw/coding-router"><img src="https://agentmods.dev/badge/skills/kylinmountain/nano-claw/coding-router/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/skills/kylinmountain/nano-claw/coding-router"><img src="https://agentmods.dev/badge/skills/kylinmountain/nano-claw/coding-router.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 | $0.00016 | $0.00328 |
| Opus 5.5 | $0.00006 | $0.00131 |
| Sonnet 5.5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
coding-router 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 1mo 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.
What it actually says
Coding Router Skill
Purpose
This skill helps decide whether to:
- Solve coding tasks directly with local tools, or
- Delegate to the external coding CLI via
run_external_coder.
Decision Rules
Prefer local tools when:
- The change is small and file-scoped.
- You already have enough context.
- Fast iteration with direct edits is best.
Prefer external coder when:
- The request is broad, multi-file, or architecture-level.
- The user explicitly asks to use Gemini CLI / Codex.
- You need specialized coding-agent behavior.
Workflow
- Briefly explain your plan.
- Gather minimal context (read/search files).
- Decide local vs delegated execution.
- If delegated, call
run_external_coderwith a precisetaskand optionalcontext. - Validate results (tests/lint/build if relevant).
- Summarize what changed, risks, and next steps.
Safety
- Respect current approval policy and confirmation flow.
- Never expose secrets in task/context payloads.
- Keep delegated tasks scoped to the current workspace.
Delegation Prompt Quality
When calling run_external_coder, include:
- Goal and constraints
- Relevant files/paths
- Acceptance criteria
- Required validation commands
Example task structure:
- Objective: Fix failing tests in module X
- Constraints: Keep public API unchanged
- Validation:
pytest tests/test_x.py -q
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.
- 1mo ago First seen · 54 lines · 16 tokens per session scan A f000ef31b378
coding-router is a skill published in the GitHub repository KylinMountain/nano-claw (4 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 328 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
image-crop-rotate
Image processing skill for cropping images to 50% from center and rotating them 90 degrees clockwise. This skill should be used when users request image cropping to center, image rotation, or both operations combined on image files.
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
design-review-cycle
Run evidence-backed design, specification, and implementation-plan reviews through the local llm-cli-gateway stdio MCP server. Use for single-provider or complete cross-LLM design review before implementation. Covers all seven CLI request surfaces and Mistral Vibe's current accept-edits default.
model-routing
Select and dispatch llm-cli-gateway providers by live capability, target access, and task requirements. Use when choosing among Claude, Codex, Gemini, Grok, Mistral, Devin, and Cursor, or when selecting an explicit model through the local stdio gateway.
agent-codex-gate
Pattern for spawning subagents whose work must receive an evidence-backed, unconditional Codex review through the local llm-cli-gateway stdio MCP server. Use when parallel implementation tasks need an independent Codex quality gate.
multi-llm-orchestration
Orchestrate the complete llm-cli-gateway provider surface through its local stdio MCP server. Use for parallel implementation, review, session, async-job, cache-aware prompt, and cross-LLM workflows across Claude, Codex, Gemini, Grok, Mistral, Devin, and Cursor.