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 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/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/lemos999/codex-active-orchestration/context-router"><img src="https://agentmods.dev/badge/skills/lemos999/codex-active-orchestration/context-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 | $0.00026 | $0.00431 |
| Opus 5.5 | $0.00010 | $0.00172 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 5mo ago), licensed MIT. It adds 26 tokens to every session and 431 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.
context-router compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| context-routerlemos999/codex-active-orchestration | Skill | 2 | 5mo ago | MIT | A | 26 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |