agentmods.dev

seahorse-agent: Skill for Codex

.skills/seahorse-consumer-web-exposure-audit/SKILL.md

seahorse-consumer-web-exposure-audit is a skill for Codex from onceMisery/seahorse-agent. It costs 76 tokens per session (967 once invoked), scanned A, original, Apache-2.0.

A review guide for Seahorse, focused on which features are exposed in its consumer web product. Seahorse appears to be an agent platform with web, local, and enterprise capabilities.

In plain words
What is it for?
Use it when checking product modes, feature gates, administrator routes, or whether non-web capabilities are properly disabled.
Why use it?
It helps find cases where advanced features—such as shell access, files, credentials, or multi-agent connections—are accidentally available in the web product.

Skill for Codex

Written for Codex: agents/openai.yaml present.

This is onceMisery/seahorse-agent's own configuration. It tells Codex how to work on seahorse-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seahorse-agent configures →

not rated 18repo +1 1mo ago A scan 76 tokens original Apache-2.0
View source ↗ onceMisery/seahorse-agent
Reuse

Borrowing it

Nothing to install: this file belongs to onceMisery/seahorse-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/onceMisery/seahorse-agent/main/.skills/seahorse-consumer-web-exposure-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/onceMisery/seahorse-agent

Made for: Codex.

Wrote 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.

agentmods badge for seahorse-consumer-web-exposure-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/oncemisery/seahorse-agent/seahorse-consumer-web-exposure-audit/github.svg)](https://agentmods.dev/skills/oncemisery/seahorse-agent/seahorse-consumer-web-exposure-audit)
Your own site
<a href="https://agentmods.dev/skills/oncemisery/seahorse-agent/seahorse-consumer-web-exposure-audit"><img src="https://agentmods.dev/badge/skills/oncemisery/seahorse-agent/seahorse-consumer-web-exposure-audit/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.

agentmods 80×15 button for seahorse-consumer-web-exposure-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/oncemisery/seahorse-agent/seahorse-consumer-web-exposure-audit"><img src="https://agentmods.dev/badge/skills/oncemisery/seahorse-agent/seahorse-consumer-web-exposure-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00076 $0.00967
Opus 5 $0.00038 $0.00483
Sonnet 5 $0.00015 $0.00193
Haiku 4.5 $0.00008 $0.00097

Measured 12d ago against content hash ad63f7a2ab1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

seahorse-consumer-web-exposure-audit 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 12d 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.

.skills/seahorse-consumer-web-exposure-audit/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seahorse Consumer Web Exposure Audit

Overview

Audit whether the default consumer-web product path exposes non-Web, local, mesh, or enterprise-only capabilities. Keep the review evidence-based: cite exact files/lines, distinguish already-gated surfaces from real exposure, and recommend the smallest fix.

Start Set

Read only the relevant docs and code for the requested worktree. Prefer:

  • docs/company-agent/c-web-ai-infra-phases/01-web-task-runtime.md
  • docs/company-agent/c-web-ai-infra-phases/02-research-web-agent.md
  • docs/company-agent/c-web-ai-infra-phases/03-personalization-operations.md
  • docs/company-agent/c-web-ai-infra-phases/04-advanced-extension-boundary.md
  • docs/company-agent/ai-infra-phases/05-connectors-credentials-sandbox.md
  • docs/company-agent/ai-infra-phases/07-multi-agent-a2a-mesh.md
  • Any non-Web remediation or handoff doc named by the user.

If a Chinese filename is hard to type, locate it with:

rg --files docs | rg "非 Web|过渡|c-web-ai-infra|ai-infra-phases|handoff"

Workflow

  1. Confirm the product baseline:

    • ProductMode.DEFAULT and config default must be CONSUMER_WEB.
    • AdvancedFeatureGate must force-disable advanced features for CONSUMER_WEB, even if config flags are true.
    • Tests should cover default consumer-web denial and explicit enterprise/advanced allowance.

  2. Build an exposure inventory with rg:

rg -n "ProductMode|AdvancedFeatureGate|AdvancedFeature|ToolProviderExposurePolicy|consumer-web|sandbox|shell|filesystem|local|MCP|OpenAPI|connector|credential|secret|A2A|mesh|handoff|rollout|readiness|enterprise|admin" .
  1. Check backend surfaces:
    • Controllers under seahorse-agent-adapter-web/src/main/java/.../web.
    • Default constructors and Spring constructors; both must preserve safe defaults.
    • AdvancedFeature enum coverage for each non-Web or enterprise capability.
    • ToolProviderExposurePolicyPort and tool registration paths; local/shell/filesystem/handoff tools must not enter default consumer-web tool sets.
    • Spring auto-configuration paths that can register local agent, sandbox, connector, A2A, or handoff capabilities without the web controller being called.

Read the full file on GitHub · 84 lines

Files

What ships with it

1 file 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.

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. 12d ago First seen · 84 lines · 76 tokens per session scan A ad63f7a2ab1a

Subscribe to this mod's changes

seahorse-consumer-web-exposure-audit is a skill published in the GitHub repository onceMisery/seahorse-agent (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 967 once invoked, about $0.0004 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.

Building agentsSecurity
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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens