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/anomalyco/models.dev/audit-reasoning-optionsnpx skills add anomalyco/models.dev --skill audit-reasoning-optionsgit clone --depth 1 https://github.com/anomalyco/models.devWrote 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/anomalyco/models.dev/audit-reasoning-options)<a href="https://agentmods.dev/skills/anomalyco/models.dev/audit-reasoning-options"><img src="https://agentmods.dev/badge/skills/anomalyco/models.dev/audit-reasoning-options.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 | $0.00041 | $0.01494 |
| Opus 5 | $0.00020 | $0.00747 |
| Sonnet 5 | $0.00008 | $0.00299 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
audit-reasoning-options 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 4d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Reasoning Options
AGENTS.md → Reasoning options is authoritative. This skill is the workflow.
Provider capability = this host’s HTTP request surface (not the npm package, SDK types, or UI).
Schema shapes
[[reasoning_options]]
type = "toggle"
[[reasoning_options]]
type = "effort"
values = ["low", "medium", "high"]
[[reasoning_options]]
type = "budget_tokens"
min = 1_024
max = 32_000
effortvalues may includenull,none,minimal,low,medium,high,xhigh,max,default— never dump the full enum.budget_tokens= reasoning tokens only, notmax_tokens. Bounds only when verified.[]= model reasons, no caller control. Omitted = not authored (invalid oncereasoning = true).
Step 1 — classify the host (role, not npm)
| Kind | Definition | Options source |
|---|---|---|
| First-party lab | providers/<id> is the model creator (OpenAI, Anthropic, DeepSeek, Alibaba, Google, …) |
That lab’s docs + existing providers/<lab>/ entries |
| Multi-model relay | Hosts many labs (OpenRouter, aggregators, most new “OpenAI-compatible” startups) | Lab entry for the underlying model + same-surface relay peers |
Critical: npm = "@ai-sdk/openai-compatible" is used by both labs (DeepSeek, Alibaba) and relays. It does not mean “apply GPT L/M/H gateway defaults.”
- DeepSeek first-party:
thinking.type+reasoning_efforthigh|max - Alibaba first-party:
enable_thinking+ oftenthinking_budget; Responses API may usereasoning.effort - A random relay of GPT-5.4: usually passthrough
reasoning_effortwith GPT-like levels
Never compare a native Anthropic Messages route to an OpenAI chat-completions relay as if they shared one control surface.
Step 2 — establish options
- Resolve underlying model (
base_model/ lab id). - Read first-party
providers/<lab>/models/…for that model. - If authoring a relay, also sample 1–2 established relays of the same model.
- Copy the intersection that this host can actually expose:
- Effort values from native/peers (may be
high/maxonly, orlow/medium/high, or includenone/xhigh, …) - Toggle if native/peers have a real on/off and this host forwards it
- Budget only if a reasoning-budget field exists on this path
- Effort values from native/peers (may be
- On relays: if native/peers have caller controls, do not write
[]from uncertainty. - On labs: match that lab; do not paste another lab’s enum.
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.
- 4d ago First seen · 136 lines · 41 tokens per session scan A 24f1133d64aa
audit-reasoning-options is a skill published in the GitHub repository anomalyco/models.dev (6,680 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,494 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…