Atlas / Skills / jeremylongshore / Linear Sdk Patterns

Linear Sdk PatternsBLOCK

skills/jeremylongshore/linear-sdk-patterns

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
BLOCK
Grade
D
Trust score
69 /100
Version
1.13.0
Hosts
2 documented
License
MIT
Stars
2,824
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-09
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
cursormentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: linear-sdk-patterns
description: >-
  Implement current Linear TypeScript SDK query, mutation, pagination, raw GraphQL, and error-handling patterns. Use when building or refactoring a typed Linear adapter. Trigger with "use Linear SDK", "refactor Linear client", or "write typed Linear GraphQL".
argument-hint: "[repository-path] [query|mutation|pagination|raw-graphql]"
allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit
version: 1.13.0
author: Jeremy Longshore <[email protected]>
license: MIT
tags:
- saas
- linear
- sdk-patterns
model: inherit
effort: high
compatibility: Designed for Claude Code; live verification requires network access and an approved Linear workspace credential
---
# Linear TypeScript SDK Patterns

## Overview

Keep SDK mechanics inside a bounded adapter and expose domain-shaped results rather than generated model objects throughout the application.

## Prerequisites

- The target repository, Linear workspace, environment, and accountable owner
- Current security, privacy, compliance, capacity, and change-control requirements
- An approved Linear credential only when a bounded live verification is necessary

## Tool Discipline

Use `Read`, `Glob`, and `Grep` to inspect code, configuration, and evidence. Use `WebFetch` only for current first-party Linear documentation and package metadata. Use `Write` or `Edit` only for requested implementation with known target files. Never write credentials, customer content, unrestricted environment output, or unredacted GraphQL variables.

## Current Contract

- Current SDK mutations use verb-first names such as `createIssue`, `updateUser`, and `archiveProject`.
- Connections expose `nodes`, `pageInfo`, `fetchNext`, and `fetchPrevious`; optional variables are passed in an object.
- `linearClient.client.rawRequest` supports purpose-built GraphQL, while `LinearError` exposes parsed request/response/error evidence.

## Authentication

Use a personal API key only for owner-controlled scripts, OAuth with PKCE for user-delegated applications, or an enabled client-credentials grant for approved automation. Personal keys use `Authorization: <API_KEY>`; OAuth tokens use `Authorization: Bearer <ACCESS_TOKEN>`. Store credentials server-side in an approved secret manager.

Treat app approval, team access, scope changes, credential creation, rotation, revocation, and production access as owner-approved actions.

## Instructions

1. Inspect the installed SDK version, generated types, adapter boundary, call sites, and error policy.
2. Create one client per approved auth context and inject it; never construct clients throughout business code.
3. Wrap SDK models in domain functions that accept stable IDs and return minimum typed projections.
4. Paginate every connection explicitly and expose checkpoints for long-running synchronization.
5. Use raw GraphQL only when it measurably reduces fields or fan-out; keep operation names and variables typed.
6. Normalize `LinearError` and GraphQL partial errors into retryable, terminal, and reconciliation-required outcomes.

## Approval Boundaries

Do not create, reveal, rotate, or revoke credentials; authorize an OAuth app; change scopes or team access; create, mutate, archive, or delete workspace data; configure or re-enable webhooks; import or export data; change roles, SCIM, or audit streaming; transmit diagnostics; change paid entitlements; or perform another production mutation without explicit approval from the accountable owner. Keep diagnosis read-only unless implementation was requested.

## Output

Return the workspace and team scope, auth mode without credential value, files and contracts inspected, exact operation names, evidence collected, validation result, sensitive fields redacted, remaining risk, accountable owner, approval state, and rollback or next action.

## Error Handling

| Condition | Response |
|---|---|
| Method missing | Compare code with the installed generated SDK and the verb-first mutation contract. |
| Connection truncated | Follow `pageInfo` or SDK page helpers until the required boundary is reached. |
| Model leaks across layers | Map it to a stable application-owned type at the adapter boundary. |
| Raw query drifts | Validate against current introspection/generated schema and add a contract test. |

## Examples

Use a compact handoff that makes scope, mutation authority, and verification evidence reviewable.

Input:

```text
adapter=issues; operation=listUpdated; page-size=25; checkpoint=cursor
```

Expected handoff:

```text
client=injected; projection=minimal; pagination=explicit; errors=normalized
```

## Resources

- [Skill-specific official documentation](references/official-docs.md)
- [Linear developer documentation index](https://linear.app/llms.txt)
- [Linear GraphQL API](https://linear.app/developers/graphql.md)
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

HIGHPrompt injection · prompt.credential_read · CWE-94, CWE-1427
SKILL.md:16
compatibility: Designed for Claude Code; live verification requires network access and an approved Linear workspace credential
Why it matters. asks the agent to read credentials
HIGHPrompt injection · prompt.credential_read · CWE-94, CWE-1427
SKILL.md:44
Treat app approval, team access, scope changes, credential creation, rotation, revocation, and production access as owner-approved actions.
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__linear-sdk-patterns.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-094f83675ca38aBLOCKD69first audit
06

Questions

What does the Linear Sdk Patterns skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Linear Sdk Patterns safe to install?

No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What can Linear Sdk Patterns access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Linear Sdk Patterns work with?

Its documentation mentions claude-code and cursor. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-09. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement