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 skills/lemos999/codex-active-orchestration/context-routernpx skills add lemos999/codex-active-orchestration --skill context-routergit clone --depth 1 https://github.com/lemos999/codex-active-orchestrationWrote 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/lemos999/codex-active-orchestration/context-router)<a href="https://agentmods.dev/skills/lemos999/codex-active-orchestration/context-router"><img src="https://agentmods.dev/badge/skills/lemos999/codex-active-orchestration/context-router.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00431 |
| Opus 5 | $0.00013 | $0.00216 |
| Sonnet 5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
context-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 5d 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
Context Router
Name class/weight: tiny, standard, or heavy: coding, review, research, assembly, measurement, delegation, explanation, command. Choose smallest finishable path; load only required files/tools/skills/refs.
If intent is unclear, interview before implementation, research, broad inspection, or explanation. Ask 1 to 3 short questions deciding advice, design, implementation, comparison, verification, packaging, explanation target, or other. Skip polish until path is clear.
Broad codebase prompts like Explain this codebase, repo walkthroughs, or project overviews are not micro until narrowed. Ask audience/scope/depth: overview, architecture, module flow, onboarding, risk review. If full tour is explicit, route macro, inspect entrypoints/manifests/README, summarize, then deepen.
Treat wording as evidence, not keyword trigger. If follow-up still leaves deliverable, mode, target, or breadth unclear, ask the next smallest path question. After answer, route to smallest needed skill and return to micro once stable.
Accounting is routing. If invoked, context-router is used even when its file was not opened. Never report none or 0 skills after naming a skill route. Separate opened skill files from used skills. Count only actually routed/invoked skills; similar tactics do not count as output-slicing or another skill.
Coding: repo shape and likely owners before broad dirs. Research: define question/evidence before sources. Long logs/diffs/search/JSON=>output-slicing. Volatile claims=>source-fidelity; token claims=>baseline-observer; delegation=>subagent-gate; graph=>graph-locator-boundary.
Ledger: class, intent, questions, loaded files, used skills, opened skill files, omitted context, next step.
Load repo-root references/operating-philosophy.md only for unclear routing.
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.
- 5d ago First seen · 23 lines · 26 tokens per session scan A e1548dff0218
context-router is a skill published in the GitHub repository lemos999/codex-active-orchestration (2 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 431 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…