agentmods.dev

mcp-feature-builder

An implementation agent for adding or updating Linear tools in mcp-linear. Linear is a project-management and issue-tracking service, and MCP is a standard way for AI assistants to call tools.

In plain words
What is it for?
Use it to implement Linear capabilities end to end, including service methods, tool definitions, handlers, type guards, registrations, documentation, tests, and build checks.
Why use it?
It coordinates the many files involved in a new tool and checks that the service, validation, registration, documentation, and tests remain consistent.

Agent

146 +1 4d ago A scan 23 tokens original MIT
View the source file tacticlaunch/mcp-linear
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 agents/tacticlaunch/mcp-linear/mcp-feature-builder
Clone the repo
git clone --depth 1 https://github.com/tacticlaunch/mcp-linear
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00023 $0.00278
Opus 5 $0.00012 $0.00139
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured 2d ago against content hash 64d4bec18d95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-feature-builder 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 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.

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.

.github/agents/mcp-feature-builder.agent.md · 32 lines

What it actually says

You are a feature implementation specialist for the mcp-linear repository.

Your job is to add or update MCP capabilities safely and with minimal churn.

Follow this workflow:

  1. Inspect the existing domain files before introducing new structure.
  2. Check whether the capability already exists in src/services/linear-service.ts.
  3. Prefer @linear/sdk methods and generated types before using direct GraphQL.
  4. Implement or update the service method first, returning normalized plain objects.
  5. Wire the MCP surface end-to-end:
    • tool definition
    • handler
    • type guard
    • central registration
  6. Update TOOLS.md when the public tool surface changes.
  7. Add focused Jest coverage in src/__tests__.
  8. Run npm test and npm run build before finishing.

Project-specific quality bar:

  • Keep input and output contracts exact about nullability, enums, and numeric constraints.
  • Keep handlers thin.
  • Keep changes small and consistent with the surrounding domain files.
  • If you must bypass the SDK because of a stale or missing capability, explain that in code comments or the PR summary.
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 · 32 lines · 23 tokens per session scan A 64d4bec18d95

Subscribe to this mod's changes

mcp-feature-builder is an agent published in the GitHub repository tacticlaunch/mcp-linear (146 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 278 once invoked, about $0.0001 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.

Backend and APIsProject managementclaudecursorlinearmcp
Related

Other agents, from other repositories

boss-pm

需求分析 Agent，将原始诉求穿透为分层需求（显性/隐性/潜在/惊喜），产出带验收标准与优先级依据的 PRD。.

echoVic/boss-skill · 46 tokens

contributor-onboarding

The Contributor-Onboarding Agent is responsible for converting GitHub issues into structured, contributor-ready onboarding recommendations.

shep-ai/shep · 0 tokens

worker-executor

Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.

huytieu/COG-second-brain · 21 tokens

ijfw-roadmapper

Use when generating a ROADMAP.md, deriving a milestone breakdown from a project brief, or mapping requirements to deliverable slices.

FerroxLabs/ijfw · 30 tokens

ijfw-extract-learnings

Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.

FerroxLabs/ijfw · 31 tokens

planner

Specialized agent for creating detailed specifications and plans. Excels at requirement analysis, task breakdown, and dependency mapping.

drafthq/draft · 23 tokens