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 0xTitanas/codex-tier-routing --skill model-routinggit clone --depth 1 https://github.com/0xTitanas/codex-tier-routingWrote 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/0xtitanas/codex-tier-routing/model-routing)<a href="https://agentmods.dev/skills/0xtitanas/codex-tier-routing/model-routing"><img src="https://agentmods.dev/badge/skills/0xtitanas/codex-tier-routing/model-routing/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/0xtitanas/codex-tier-routing/model-routing"><img src="https://agentmods.dev/badge/skills/0xtitanas/codex-tier-routing/model-routing.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 | $0.00022 | $0.01875 |
| Opus 5.5 | $0.00009 | $0.00750 |
| Sonnet 5.5 | $0.00004 | $0.00375 |
| Haiku 4.5 | $0.00002 | $0.00187 |
Grade A, and why
model-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 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model routing
Agent profiles describe requested behavior. They do not prove which model, effort level, sandbox, or working directory a child process actually used. Treat route selection as verified only when the active Codex host supplies the observation or the bundled dispatcher returns a passing local receipt.
Check capability first
Use one of these paths:
- A Codex surface that can select a registered profile from
agents/and exposes host-controlled execution details. - The installed local dispatcher at
${CODEX_HOME:-$HOME/.codex}/bin/codex-tier.
If neither path can select and verify the requested route, keep the work in the parent session. A role name in a prompt or response is not route evidence.
Ultra and host-provided spawning
Ultra mode or another Codex surface may expose a host-provided generic spawn
tool that is separate from the local dispatcher. Do not infer that such a child
used one of this project's routes. Unless the host itself selects the registered
profile and returns equivalent execution evidence, use codex-tier for the
delegation or keep the work in the parent.
Strict mode disables the documented native multi_agent feature for new
sessions using the selected Codex home. It cannot intercept a separate tool
injected by a host application. Output from that tool must not be labeled with a
route, model, effort, sandbox, lineage, or receipt from this project.
Local dispatcher
Run the zero-model-call probe before dispatching work:
"${CODEX_HOME:-$HOME/.codex}/bin/codex-tier" probe
Also validate the active model/effort mapping without a model call:
"${CODEX_HOME:-$HOME/.codex}/bin/codex-tier" policy-check
policy-check must pass. It reports the active policy hash, resolved routes,
accepted effort values, and model_access: not_checked. Policy syntax is not
account entitlement; run a bounded canary for every changed route.
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 · 193 lines · 22 tokens per session scan A 6fbfaa6ddbb3
model-routing is a skill published in the GitHub repository 0xTitanas/codex-tier-routing (1 stars, last pushed 20d ago), licensed MIT. It adds 22 tokens to every session and 1,875 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
codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
flue
Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.
code-that-fits-in-your-head
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…
rexai-image-generation
An image-generation skill that uses RexAI to create new images from text or transform existing images from other images. It returns the result as a local file.