lenserfight: Skill for Claude Code

.agents/skills/mcp-manager/SKILL.md

mcp-manager is a skill for Claude Code from conectlens/lenserfight. It costs 88 tokens per session (1,364 once invoked), scanned A, original, MIT.

A set of instructions for creating, registering, reviewing, and debugging MCP tools in a server application. MCP is a way for an AI assistant to call tools provided by another program.

In plain words
What is it for?
Use it to add MCP tools, review changes under apps/mcp-server, or investigate authentication, RPC, OAuth, and connection-transport failures.
Why use it?
It gives tool work a consistent file layout, naming scheme, registration process, and approach to authentication and transport errors. This reduces wiring mistakes when adding or changing tools.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

This is conectlens/lenserfight's own configuration. It tells Claude Code how to work on lenserfight 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 lenserfight configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { ok, fail, zUuid } from '../../types.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to conectlens/lenserfight. 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/conectlens/lenserfight/main/.agents/skills/mcp-manager/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/conectlens/lenserfight

Made for: Claude Code.

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 mcp-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/conectlens/lenserfight/mcp-manager.svg)](https://agentmods.dev/skills/conectlens/lenserfight/mcp-manager)
Your own site
<a href="https://agentmods.dev/skills/conectlens/lenserfight/mcp-manager"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/mcp-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,364 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00088 $0.01364
Opus 5 $0.00044 $0.00682
Sonnet 5 $0.00018 $0.00273
Haiku 4.5 $0.00009 $0.00136

Measured 8d ago against content hash 01bf4e97fd97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-manager 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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/new-tool.sh, scripts/validate-tool.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/mcp-manager/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Manager

When to use

  • Adding a new tool (any domain or a new one)
  • Reviewing a PR that touches apps/mcp-server/
  • Debugging 401s, RPC errors, or transport failures
  • Changing OAuth flow or transport architecture

Layout

apps/mcp-server/src/
  main.ts               # entry: bootHttp | bootStdio
  types.ts              # ok() fail() paginated() zUuid
  config.ts             # getConfig() → McpServerConfig
  middleware/auth.ts    # resolveAuth() → AuthContext
  transport/http.ts     # HTTP + OAuth + session map
  transport/stdio.ts    # stdio (service-role, no auth)
  tools/
    lens/               # lens-*.ts  +  index.ts → registerLensTools()
    battle/             # battle-*.ts + index.ts → registerBattleTools()
    workflow/           # workflow-*.ts + index.ts → registerWorkflowTools()

Naming rule

Two separate conventions — keep them consistent:

Artifact Convention Example
File stem <domain>-<action> kebab lens-get-version.ts
MCP tool name verb_noun verb-first snake_case get_lens_version
Export function register<Domain><Action> PascalCase registerLensGetVersion
Supabase RPC fn_mcp_<domain>_<action> domain-first fn_mcp_lens_get_version

MCP tool names are verb-first so AI agents can group by action (get_*, list_*). File stems are domain-first so tools sort together on disk.

Verb prefix in use: get_* list_* create_* update_* delete_* run_* search_* set_* archive_* fork_* submit_* retry_* summarize_* find_and_run_* validate_* extract_* add_*

Multi-word actions: first action-word becomes the verb, domain slots in second. battle-submit-run.ts → tool submit_battle_run, RPC fn_mcp_battle_submit_run

Tool template

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { SupabaseClient } from '@supabase/supabase-js';
import { ok, fail, zUuid } from '../../types.js';

export function registerLensPin(server: McpServer, sb: SupabaseClient): void {
  server.tool(
    'pin_lens',                          // verb_noun — verb first
    'Pin a lens to the caller\'s profile.',
    { lens_id: zUuid },
    async ({ lens_id }) => {
      const t0 = Date.now();
      try {
        const { data, error } = (await sb.rpc('fn_mcp_lens_pin' as never, {  // fn_mcp_domain_action
          p_lens_id: lens_id,
        })) as unknown as { data: unknown; error: { message: string } | null };
        if (error) throw new Error(error.message);
        if (!data) return fail('NOT_FOUND', `Lens ${lens_id} not found`, {}, 'pin_lens', t0);
        return ok(data, 'pin_lens', t0);
      } catch (e) {
        return fail('DB_ERROR', (e as Error).message, {}, 'pin_lens', t0);
      }
    }
  );
}

Read the full file on GitHub · 128 lines

Files

What ships with it

4 files 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. 8d ago First seen · 128 lines · 88 tokens per session scan A 01bf4e97fd97

Subscribe to this mod's changes

mcp-manager is a skill published in the GitHub repository conectlens/lenserfight (18 stars, last pushed 29d ago), licensed MIT. It adds 88 tokens to every session and 1,364 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.