verify

A verification procedure for the model-gateway plugin. It tests the gateway's command-line tools and HTTP interface, which is the web-style connection used to send and receive model requests.

In plain words
What is it for?
Testing model lists, message forwarding, legacy model names, settings changes, project wiring, user fallback settings, and compatibility behavior.
Why use it?
It catches incorrect model routing, broken project settings, and conflicts between project-level and user-level configuration before real sessions depend on them.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/eigenwise/eigenwise-toolshed/verify
Any agent
npx skills add Eigenwise/eigenwise-toolshed --skill verify
Clone the repo
git clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshed

Made for: Claude Code, Codex.

Per session 1 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 486 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00001 $0.00486
Opus 5 $0.00000 $0.00243
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00049

Measured 2d ago against content hash 0f91c54006c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

verify scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. `ensure --quiet` with a temporary `~/.claude/settings.json` containing legacy settings. The command may exit nonzero when no proxy binary exists; inspect the settings mutation itself.
plugins/model-gateway/.claude/skills/verify/SKILL.md · 20 lines

What it actually says

Verify model-gateway

Use an isolated temporary home and random localhost ports. Start bin/model-gateway.js serve-shim against a tiny fake HTTP proxy that serves /v1/models and records forwarded message bodies.

Drive these surfaces:

  1. GET /v1/models through the running shim.
  2. POST /v1/messages using both current and legacy model IDs, then inspect the fake proxy's received model.
  3. ensure --quiet with a temporary ~/.claude/settings.json containing legacy settings. The command may exit nonzero when no proxy binary exists; inspect the settings mutation itself.
  4. env --write-project against a temporary project directory to check that wiring lands in that project's .claude/settings.local.json and never in a committed .claude/settings.json. Then env --write-user against a temporary HOME for the shared fallback, checking preservation of user-set values. With both set, doctor must name the project-local one as effective and fail a mode contradiction. --mode and --show-mode are retired and must exit 2.
  5. RC-compatibility mode: set CODEX_GATEWAY_HOSTS_FILE to a temp hosts file and CODEX_GATEWAY_COMPAT_PORT to a free ephemeral port (never the real 80) before starting serve-shim. With the file containing 127.0.0.1 api.anthropic.com, GET /healthz on both the main port and the compat port must report compat.hostsDetected: true and compat.port80Bound: true. With the entry absent, both must be false and the compat port must refuse connections. Pre-binding the compat port before spawning the shim proves the safe fallback: hostsDetected: true, port80Bound: false, a populated reason, and the main port still serving normally.
  6. DNS-recursion guard: require lib/request-worker.js directly and call createHostsBypassResolver({ resolve4, resolve6 }) with injected fake resolvers to confirm it never falls back to a hosts-aware lookup and errors closed when both resolvers fail.

Keep the real gateway and user settings untouched. Capture response bodies and resulting settings JSON inline.

Changes

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.

  1. 2d ago First seen · 20 lines · 1 tokens per session scan B 0f91c54006c6

Subscribe to this mod's changes

verify is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (36 stars, last pushed 4d ago), licensed MIT. It adds 1 tokens to every session and 486 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens