Atlas / Skills / jeremylongshore / Linear Common Errors

Linear Common ErrorsBLOCK

skills/jeremylongshore/linear-common-errors

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
1 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
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-common-errors
description: >-
  Diagnose Linear GraphQL and SDK failures from transport, response, and request evidence. Use when an integration returns partial data, authentication failures, rate limits, invalid input, or missing resources. Trigger with "debug Linear GraphQL", "Linear API error", or "why did Linear SDK fail".
argument-hint: "[repository-path] [redacted-error-or-request-id]"
allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit
version: 1.13.0
author: Jeremy Longshore <[email protected]>
license: MIT
tags:
- saas
- linear
- error-triage
model: inherit
effort: high
compatibility: Designed for Claude Code; live verification requires network access and an approved Linear workspace credential
---
# Linear Error Triage

## Overview

Classify a failure before changing code or credentials, because Linear can return GraphQL errors with HTTP 200 and throttling errors with HTTP 400.

## 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

- Always inspect the GraphQL `errors` array; a response can include partial `data` and errors together.
- Rate limiting is identified by `extensions.code: RATELIMITED` in an HTTP 400 GraphQL response, not by assuming HTTP 429.
- The SDK exposes parsed `LinearError` details including query, variables, status, data, raw error, and per-error path/type when available.

## 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. Capture the operation name, HTTP status, GraphQL error code/path, SDK version, and redacted rate headers.
2. Separate authentication, authorization, input, not-found, complexity, endpoint-budget, and service-health failures.
3. Reproduce with the smallest read-only query using the same auth mode; do not paste tokens or full customer variables.
4. For partial data, decide whether the caller must reject the whole response or can use explicitly safe fields.
5. For throttling, follow reset metadata, shrink requested fields/pages, and coordinate all workers sharing the user or app budget.
6. Return the root-cause evidence, bounded remediation, and a regression assertion.

## 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 |
|---|---|
| HTTP 200 plus `errors` | Treat it as an application failure unless partial-data handling is explicitly designed. |
| HTTP 400 plus `RATELIMITED` | Honor reset data and reduce request or complexity pressure. |
| Forbidden | Verify team visibility and exact OAuth scope; do not broaden access by default. |
| Unknown schema field | Check introspection, SDK version, and deprecation notices before renaming code. |

## Examples

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

Input:

```text
status=200; errors[0].path=issueCreate; sdk=95.0.0; variables=redacted
```

Expected handoff:

```text
class=graphql-application-error; retry=no; regression=payload-error-check
```

## 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-common-errors.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 Common Errors 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 Common Errors 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 Common Errors access on my machine?

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

Which assistants does Linear Common Errors work with?

Its documentation mentions claude-code. 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