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.
npx agentmods add instructions/tacticlaunch/mcp-linear/copilot-instructionsgit clone --depth 1 https://github.com/tacticlaunch/mcp-linearWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00517 | $0.00517 |
| Opus 5 | $0.00259 | $0.00259 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
mcp-linear copilot-instructions.md 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Linear Repository Instructions
This repository is an MCP server for Linear, not an application. Most work in this repo adds, updates, or reviews Linear-facing MCP tools.
Repository Map
src/services/linear-service.ts: main integration layer for@linear/sdkand the place where MCP-facing response normalization should happen.src/tools/definitions/*.ts: MCP tool definitions and input/output schemas, grouped by domain.src/tools/handlers/*.ts: thin handlers that validate arguments, delegate toLinearService, and log errors.src/tools/type-guards.ts: runtime validation for tool arguments.src/tools/definitions/index.tsandsrc/tools/handlers/index.ts: central registration.src/__tests__/*.ts: focused Jest coverage for service behavior and tool wiring.TOOLS.md: user-facing tool inventory and planned work.package.json: package metadata.
How To Add Or Change A Tool
- Start by checking whether the capability already exists in
src/services/linear-service.ts. - Prefer
@linear/sdkmethods and generated types first. - Use direct GraphQL only when the SDK is missing support or ships a stale query. If you do this, keep the query narrow and document why.
- Keep service methods responsible for returning normalized plain objects, not raw SDK entities.
- Keep handlers thin.
- Keep
input_schema,output_schema, type guards, and normalized service output aligned exactly, especially around nullable fields and enums. - Register every new tool in both index files.
- Update
TOOLS.mdwhen the public tool surface changes.
Validation
- Always run
npm testandnpm run buildbefore considering work complete. - Use
npm run dev -- --token YOUR_LINEAR_API_TOKENfor local server development. - Use
npm run inspect -- -e LINEAR_API_TOKEN=YOUR_LINEAR_API_TOKENwhen validating the local MCP server with the inspector.
Project-Specific Pitfalls
- This repo frequently needs careful SDK contract inspection. Check
node_modules/@linear/sdk/dist/_generated_sdk.d.tsand_generated_documents.d.tsbefore guessing field names or mutation inputs. - Some Linear product naming does not match SDK naming. For example, saved views are
CustomViewin the API and SDK. - Review changes carefully for schema drift between service output, tool definitions, and type guards.
- Keep changes minimal and domain-local. Prefer extending an existing domain file over introducing new structure unless the domain is clearly separate.
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.
- 2d ago First seen · 39 lines · 517 tokens per session scan A 73e124580827
mcp-linear copilot-instructions.md is an instructions file published in the GitHub repository tacticlaunch/mcp-linear (146 stars, last pushed 4d ago), licensed MIT. It adds 517 tokens to every session, about $0.0026 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.
Other instructions, from other repositories
linear-claude-skill CLAUDE.md
Instructions for wrsmith108/linear-claude-skill, covering claude.md, project overview, common commands, run setup check (validates linearapikey and dependencies) and high-level operations cli.
lineark CLAUDE.md
Instructions for flipbit03/lineark, covering claude.md — lineark, what is this, workspace layout, key commands and writing online tests: the three pillars.
planr AGENTS.md
Instructions for instructa/planr: Planr is being shaped into a local-first planning and execution coordination tool for Codex, Claude Code, Cursor, and generic MCP clients.
Ocul-PM AGENTS.md
Instructions for bunhine0452/Ocul-PM, covering ocul-pm 작업 기록 규칙, 0. 시작하기 전 — 과거를 먼저 찾는다, 1. 언제 기록하는가 (5 trigger), 2. 일지 파일 규격 (도구가 없을 때만) and 3. 금지.
agentic-config AGENTS.md
Instructions for WaterplanAI/agentic-config, covering project guidelines, environment & tooling, core rules, skill triggering and content & pii.
odin-sentinel CLAUDE.md
Instructions for bradheitmann/odin-sentinel, covering odin sentinel guidance for claude, public role contract, claude-specific notes and output shape.