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 xiaojiou176-open/codeflow --skill openvibecoding-adoption-routergit clone --depth 1 https://github.com/xiaojiou176-open/codeflowWrote 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/xiaojiou176-open/codeflow/openvibecoding-adoption-router)<a href="https://agentmods.dev/skills/xiaojiou176-open/codeflow/openvibecoding-adoption-router"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/codeflow/openvibecoding-adoption-router.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00350 |
| Opus 5 | $0.00016 | $0.00175 |
| Sonnet 5 | $0.00006 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
codeflow-adoption-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 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.
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
Purpose
Use this skill when a coding-agent workflow needs the shortest honest Codeflow entrypoint.
The job is to pick the right adoption lane first instead of treating every host tool as the same kind of plugin system.
Read Order
README.mddocs/README.mddocs/compatibility/index.htmldocs/integrations/index.html- One deeper lane only:
docs/mcp/index.htmldocs/skills/index.htmldocs/builders/index.htmldocs/use-cases/index.html
Use It To Choose A Lane
- Start with read-only MCP when the first need is machine-readable inspection.
- Start with skills when the first need is repeatable repo-owned behavior.
- Start with builders when the first need is package-level reuse.
- Start with use cases when the first need is proof-first product understanding.
Guardrails
- Do not describe Codeflow as a hosted operator product.
- Do not describe the public MCP surface as write-capable.
- Do not claim this bundle is a published Codex or OpenClaw listing.
- Do not describe Claude Code as if it has a Codeflow marketplace package.
- Keep
task_contractas the only execution authority.
Done Signal
The adoption path is correct only when the chosen lane matches the real job and the wording stays below official-listing or hosted-product claims.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 47 lines · 32 tokens per session scan A 9c4a0c112ef1
codeflow-adoption-router is a skill published in the GitHub repository xiaojiou176-open/codeflow (207 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 350 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 skills, from other repositories
session_capture
AUTO-CAPTURE — Use after EVERY meaningful user turn to persist the conversation into TokenKnows. Trigger on ANY user message that is NOT a one-word ack ("ok"/"thanks"). Without this skill, the conversation is silently lost from the user's TokenKnows workbench. Calls submitsessionevents MCP tool. This is the only path…
distill
A skill that turns the current Claude conversation into a structured document through the TokenKnows service. It supports formats such as weekly reports, technical designs, architecture decision records, incident reviews, books, skills, and knowledge graphs.
fastapi
FastAPI best practices + Pydantic. Use when building or reviewing FastAPI APIs.
thinkroom-operate
Operate Thinkroom research jobs.
thinkroom-install
Install and verify Thinkroom skills.
tokenknows-knowledge
A local knowledge search tool for finding project decisions, documents, and relationships between people, concepts, events, and other project items across previous sessions.