backlog-mcp-server: Skill for Claude Code

.claude/skills/implement-backlog-api-tool/SKILL.md

implement-backlog-api-tool is a skill for Claude Code from nulab/backlog-mcp-server. It costs 67 tokens per session (501 once invoked), scanned A, original, MIT.

A development guide for adding a tool that connects an MCP server to a Backlog API endpoint.

In plain words
What is it for?
It identifies the endpoint, parameters, and response fields, checks the backlog-js method, studies similar tools, and creates the required source files.
Why use it?
It turns an API specification into an implementation that follows the existing client and project patterns.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is nulab/backlog-mcp-server's own configuration. It tells Claude Code how to work on backlog-mcp-server 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 backlog-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nulab/backlog-mcp-server. 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/nulab/backlog-mcp-server/main/.claude/skills/implement-backlog-api-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nulab/backlog-mcp-server

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 implement-backlog-api-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/nulab/backlog-mcp-server/implement-backlog-api-tool/github.svg)](https://agentmods.dev/skills/nulab/backlog-mcp-server/implement-backlog-api-tool)
Your own site
<a href="https://agentmods.dev/skills/nulab/backlog-mcp-server/implement-backlog-api-tool"><img src="https://agentmods.dev/badge/skills/nulab/backlog-mcp-server/implement-backlog-api-tool/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 implement-backlog-api-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/nulab/backlog-mcp-server/implement-backlog-api-tool"><img src="https://agentmods.dev/badge/skills/nulab/backlog-mcp-server/implement-backlog-api-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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 $0.00067 $0.00501
Opus 5.5 $0.00027 $0.00200
Sonnet 5.5 $0.00013 $0.00100
Haiku 4.5 $0.00007 $0.00050

Measured 2mo ago against content hash e23bcbffa322, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

implement-backlog-api-tool 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/implement-backlog-api-tool/SKILL.md · 63 lines

What it actually says

Implement a Backlog API Tool

Overview

Implement a new MCP tool for the Backlog API endpoint documented at $ARGUMENTS.

Steps

1. Read the API spec

Fetch the documentation page using the fetch_webpage tool with the URL $ARGUMENTS and extract the following:

Identify:

  • HTTP Method – GET, POST, PATCH, DELETE, etc.
  • Endpoint path – e.g. /api/v2/space
  • Parameters – name, type, required/optional, description
  • Response fields – JSON structure returned by the API

2. Check the backlog-js client

Find the corresponding method in the backlog-js type definitions:

grep "methodName" node_modules/backlog-js/dist/types/backlog.d.ts

Replace methodName with the actual method name (e.g. getSpace, postIssue). If unsure of the name, read the full file to browse all available methods:

cat node_modules/backlog-js/dist/types/backlog.d.ts

Use the method's name and type signature as the basis for implementation.

3. Read an existing similar tool for reference

cat src/tools/getSpace.ts
cat src/handlers/builders/composeToolHandler.ts

4. Implement the tool

Create or update these files following the existing patterns:

src/tools/<toolName>.ts
  • Define the tool name, description, and input schema using zod
  • Map each API parameter to a zod field with an appropriate description
  • Set outputSchema to a Zod schema matching the API response shape (see src/types/zod/backlogOutputDefinition.ts)
  • Set importantFields to the subset of fields that are most relevant to the user
  • Implement handler to call the corresponding backlog-js client method
src/tools/tools.ts
  • Register the new tool so it is picked up by the server
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. 2mo ago First seen · 63 lines · 67 tokens per session scan A e23bcbffa322

Subscribe to this mod's changes

implement-backlog-api-tool is a skill published in the GitHub repository nulab/backlog-mcp-server (243 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 501 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

implement-backlog-api-tool compared with skills from other repositories

implement-backlog-api-tool next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
implement-backlog-api-toolnulab/backlog-mcp-serverSkill2435d agoMITA67Claude Code
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0kyesterdayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code