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 ucsahinn/codex-chef --skill adaptive-agent-routinggit clone --depth 1 https://github.com/ucsahinn/codex-chefWrote 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/ucsahinn/codex-chef/adaptive-agent-routing)<a href="https://agentmods.dev/skills/ucsahinn/codex-chef/adaptive-agent-routing"><img src="https://agentmods.dev/badge/skills/ucsahinn/codex-chef/adaptive-agent-routing.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 | $0.00055 | $0.00276 |
| Opus 5 | $0.00028 | $0.00138 |
| Sonnet 5 | $0.00011 | $0.00055 |
| Haiku 4.5 | $0.00006 | $0.00028 |
Grade A, and why
adaptive-agent-routing 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 7d 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
Adaptive Agent Routing
Select routes by expected value, not by catalog match alone.
Workflow
- Classify the task shape and identify the smallest owning surface.
- Read global-working-agreements.md only when the detailed route, specialist map, alias policy, or MCP boundary is relevant.
- Preserve the active user's profile, model, and reasoning settings. Agent role files must not pin them.
- Delegate only for independent parallel work, noisy log or research isolation, or explicit user-requested agent work.
- Treat ten threads as capacity for concurrent sessions. Normally use one agent and no more than four agents for one task.
- Emit one
Routing plan:update and oneRouting result:summary instead of per-surface narration. - Keep destructive, credentialed, account, database, publish, deploy, and external-write actions approval-gated.
Output Contract
Return selected and skipped surfaces, summarized evidence, commands run, and blockers. Do not paste raw agent transcripts or large logs.
What ships with it
2 files 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.
- 7d ago First seen · 23 lines · 55 tokens per session scan A b33609a06cee
adaptive-agent-routing is a skill published in the GitHub repository ucsahinn/codex-chef (6 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 276 once invoked, about $0.0003 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
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
review-response
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
skill-development
This skill should be used when the user asks to create a new skill, repair an existing skill, improve trigger descriptions, reorganize skill structure, or make a Claude skill more reusable and internally consistent.