gate-local-mcp: Skill for Claude Code

.agent/skills/gate-mcp-tool-conventions/SKILL.md

gate-mcp-tool-conventions is a skill for Claude Code, Codex from gate/gate-local-mcp. It costs 61 tokens per session (592 once invoked), scanned A, original, MIT.

Development rules for adding, renaming, or reviewing tools in the Gate MCP server, including naming, write-operation detection, and end-to-end test counts.

In plain words
What is it for?
Registering tools in the server, checking SDK-derived names, updating write-verb lists, and adjusting module counts in end-to-end tests.
Why use it?
It prevents new tools from using inconsistent names or being classified incorrectly, and keeps related tests updated.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is gate/gate-local-mcp's own configuration. It tells Claude Code and Codex how to work on gate-local-mcp 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 gate-local-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node tests/e2e.cjs # must show N/N passed, 0 FAILED.

Reuse

Borrowing it

Nothing to install: this file belongs to gate/gate-local-mcp. 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/gate/gate-local-mcp/main/.agent/skills/gate-mcp-tool-conventions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gate/gate-local-mcp

Made for: Claude Code, 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 gate-mcp-tool-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/gate/gate-local-mcp/gate-mcp-tool-conventions/github.svg)](https://agentmods.dev/skills/gate/gate-local-mcp/gate-mcp-tool-conventions)
Your own site
<a href="https://agentmods.dev/skills/gate/gate-local-mcp/gate-mcp-tool-conventions"><img src="https://agentmods.dev/badge/skills/gate/gate-local-mcp/gate-mcp-tool-conventions/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 gate-mcp-tool-conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/gate/gate-local-mcp/gate-mcp-tool-conventions"><img src="https://agentmods.dev/badge/skills/gate/gate-local-mcp/gate-mcp-tool-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 592 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 $0.00061 $0.00592
Opus 5 $0.00030 $0.00296
Sonnet 5 $0.00012 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 9d ago against content hash ddbdb9ba16b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gate-mcp-tool-conventions 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 9d 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.

.agent/skills/gate-mcp-tool-conventions/SKILL.md · 61 lines

What it actually says

Gate MCP Tool Conventions

Read references/naming-rules.md for the full naming derivation table, module abbreviation map, and write-verb list.

Checklist for every new tool

1. Derive the tool name from the SDK method

Look up the SDK method in node_modules/gate-api/dist/api/*.d.ts. Strip the class/instance prefix and convert to snake_case:

{SDK method (CamelCase, no class prefix)} → cex_{module_abbr}_{snake_case}

P2P exception: SDK uses p2pMerchant{Category}{Verb} — strip p2pMerchant, keep {category}_{verb} order as-is. Do NOT reorder to verb-first.

See references/naming-rules.md for examples and the full module abbreviation map.

2. Check write-verb detection

After naming, verify the tool is classified correctly:

  • isWriteTool checks index 2 OR index 3 (0-based) against WRITE_VERBS
  • If a new write tool's verb lands at index 2 or 3 → no changes needed
  • If the verb is not in WRITE_VERBS → add it to both:
    • src/utils.tsWRITE_VERBS set
    • tests/e2e.cjsWRITE_VERBS set (must stay in sync)

3. Update e2e test MODULE_COUNTS

In tests/e2e.cjs, update the entry for the affected module:

const MODULE_COUNTS = {
  mymodule: { total: N+1, readonly: R, write: W },
  //                ^^^^ increment total; increment write if write tool
};

readonly = totalwrite.

4. Build and test

npm run build
node tests/e2e.cjs   # must show N/N passed, 0 FAILED

Fix any failures before committing.


Updating this skill

When a new naming rule or convention is established — e.g., a new SDK that uses a different prefix pattern, a new module abbreviation, a new write verb, or a change to the index check rule — update references/naming-rules.md with the rule and an example. Add a step to the checklist above if it requires a new action.

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. 9d ago First seen · 61 lines · 61 tokens per session scan A ddbdb9ba16b2

Subscribe to this mod's changes

gate-mcp-tool-conventions is a skill published in the GitHub repository gate/gate-local-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 592 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.

Related

Other skills, from other repositories

api-tester

A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.

laolaoshiren/claude-code-skills-zh · 86 tokens

backend/testing-guide

A guide for writing backend tests: small unit tests, tests that check connected parts such as an API and database, and end-to-end tests that follow a complete user flow.

echoVic/boss-skill · 30 tokens

endpoint-probe

Probes each major Agent Monitor API route — /api/stats, /api/analytics, /api/sessions, /api/pricing/cost, /api/workflows/runs, /api/cc-config/overview — and reports each one's HTTP status, latency, and response shape, flagging which are reachable. Use to verify a dashboard install is wired up correctly.

hoangsonww/Claude-Code-Agent-Monitor · 80 tokens

emulate-seed

Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS, Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs — full state machines, not mocks. Use when setting up test environments, CI pipelines, integration tests…

yonatangross/orchestkit · 86 tokens

Kafka Event-Driven Testing

Test Kafka-based event-driven systems, producer and consumer integration tests with Testcontainers, schema compatibility gates, idempotency and ordering verification, dead-letter handling, and end-to-end event flow assertions.

PramodDutta/qaskills · 45 tokens

api-smoke-testing

Start the dev server, discover API routes from the codebase, hit every endpoint, and report which ones return errors.

spencerpauly/awesome-cursor-skills · 29 tokens