Linear Core Workflow ABLOCK
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Overview
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
4f83675ca38aOBSERVED · 2026-10-09Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
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-core-workflow-a description: >- Implement a controlled Linear issue lifecycle from discovery through create, update, relation, comment, and archive actions. Use when automating issue operations with the GraphQL API or TypeScript SDK. Trigger with "automate Linear issues", "build an issue workflow", or "update Linear issue states". argument-hint: "[repository-path] [team-key] [dry-run|apply]" allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit version: 1.13.0 author: Jeremy Longshore <[email protected]> license: MIT tags: - saas - linear - issue-workflow model: inherit effort: high compatibility: Designed for Claude Code; live verification requires network access and an approved Linear workspace credential --- # Linear Issue Lifecycle Workflow ## Overview Build an issue workflow that resolves workspace-owned identifiers first and treats each write as a reviewable, reversible business action. ## 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 - `issueCreate` requires a team ID; without a state ID Linear selects the team's first Backlog state, or Triage when enabled. - The SDK uses verb-first mutation names such as `createIssue`, `updateIssue`, and `archiveIssue`. - Changes made during the first three minutes after issue creation are treated as part of creation and do not produce activity-log entries. ## 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. Resolve the authenticated viewer, organization, target team, workflow states, labels, and assignees using read-only queries. 2. Translate the requested business transition into an explicit create/update/comment/relation plan with stable IDs. 3. Validate required fields, visibility, duplicate policy, and whether Triage changes the default initial state. 4. Preview the exact mutation variables with sensitive or personal fields redacted. 5. After approval, perform one mutation and verify both GraphQL errors and payload success before the next action. 6. Return identifiers, resulting state, reconciliation query, and rollback or archive instructions. ## 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 | |---|---| | Team or state not found | Stop and list visible candidates; never fall back to the first team silently. | | Duplicate issue | Reconcile by an approved external key or canonical URL before creating. | | Partial mutation response | Treat any GraphQL error as unresolved and verify the issue by ID. | | Rollback requested | Prefer a documented compensating update or archive; do not delete history casually. | ## Examples Use a compact handoff that makes scope, mutation authority, and verification evidence reviewable. Input: ```text team=ENG; action=create; title=redacted-summary; mode=dry-run ``` Expected handoff: ```text team-id=resolved; mutation=issueCreate; approval=pending; rollback=archive ``` ## 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)
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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
compatibility: Designed for Claude Code; live verification requires network access and an approved Linear workspace credential
Treat app approval, team access, scope changes, credential creation, rotation, revocation, and production access as owner-approved actions.
Gates applied: no_behavioural_pass.
4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__linear-core-workflow-a.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 4f83675ca38a | BLOCK | D | 69 | first audit |
Questions
What does the Linear Core Workflow A 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 Core Workflow A 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 Core Workflow A access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Linear Core Workflow A 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.