linear-cost-tuning — Claude Code skill: what it does, how to install
linear-cost-tuning analyzes Linear API consumption, trims GraphQL query complexity, and shifts redundant polling loops to push webhooks.
MIT 1 installs ★ 2,935 updated 2026-10-29
npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a claude-codeWhat linear-cost-tuning does
The skill audits Linear integration code to cut infrastructure and quota usage. Using Read, Glob, and Grep, it tracks request volumes, GraphQL complexity budgets, and payload sizes across workflows.
Rather than assuming a flat pricing model, it treats cost as compute, queue, and quota overhead. It spots aggressive polling patterns to replace them with webhooks, narrows requested fields, and bounds page sizes.
Diagnostics stay strictly read-only. The skill refuses to alter Linear workspace data, create live webhooks, or rotate credentials without explicit owner sign-off.
What it helps with
- switch resource-heavy Linear polling to webhooks
- trim GraphQL query complexity and page sizes
- establish request budgets against Linear quota limits
- eliminate duplicate reads and broad field selections
Example prompts for the agent
- Reduce Linear API load for the integration in
./services/linear-sync - Budget Linear queries and replace polling loops with webhooks
- Tune Linear integration cost and inspect GraphQL payload complexity
How to install linear-cost-tuning
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a claude-code2Manually: put the files in place
~/.claude/skills/linear-cost-tuning/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/linear-cost-tuning/
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a codex2Manually: put the files in place
.agents/skills/linear-cost-tuning/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a cursor2Manually: put the files in place
.cursor/skills/linear-cost-tuning/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install jeremylongshore/tons-of-skills-marketplace skills/.curated/linear-cost-tuning2Manually: put the files in place
.github/skills/linear-cost-tuning/SKILL.md1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a gemini-cli2Platform CLI
gemini skills install https://github.com/jeremylongshore/tons-of-skills-marketplace --path skills/.curated/linear-cost-tuningManually: put the files in place
.devin/skills/linear-cost-tuning/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about linear-cost-tuning
How do I install linear-cost-tuning in Claude Code?
Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill linear-cost-tuning -a claude-code.
What does linear-cost-tuning do?
It audits Linear integrations, establishes query complexity budgets, and replaces wasteful polling with event-driven webhooks.
Does linear-cost-tuning modify Linear workspace credentials or data?
No. The inspection runs in read-only mode and avoids credential changes or production mutations without explicit confirmation.
Source text
SKILL.md · MIT
--- name: linear-cost-tuning description: >- Analyze and reduce the infrastructure and quota cost of a Linear integration through workload accounting, query budgets, and push-based updates. Use when a sync is wasteful, throttled, or expensive to operate. Trigger with "reduce Linear API load", "budget Linear queries", or "tune Linear integration cost". argument-hint: "[repository-path] [workload-or-budget]" allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit version: 1.13.0 author: Jeremy Longshore <[email protected]> license: MIT tags: - saas - linear - capacity-tuning model: inherit effort: high compatibility: Designed for Claude Code; live verification requires network access and an approved Linear workspace credential --- # Linear Workload and Capacity Tuning ## Overview Treat cost as the integration's compute, queue, storage, support, and quota consumption; do not claim a fixed Linear API price from cached documentation. ## 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 - Linear publishes request and complexity budgets, not a universal per-request price; plan and contract entitlements are dynamic. - Polling is discouraged; webhooks are the primary change signal when supported. - Filtering, explicit page sizes, narrow field selection, and updated-time ordering reduce both query complexity and local processing. ## 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. Measure requests, complexity, payload bytes, queue time, retries, storage growth, and operator toil by workflow. 2. Separate required freshness from habitual polling and replace supported polling loops with verified webhooks. 3. Set per-workload request and complexity budgets below the applicable shared limits. 4. Reduce fields, page sizes, fan-out, duplicate reads, and retention while preserving correctness and audit needs. 5. Load-test with synthetic data and compare before/after throughput, freshness, and failure recovery. 6. Verify current plan terms with the workspace owner before presenting monetary savings. ## 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 | |---|---| | No baseline | Instrument the workload before proposing savings. | | Quota confused with price | Report request/complexity consumption separately from commercial terms. | | Webhook gap | Keep a bounded reconciliation job for unsupported or missed events. | | Optimization changes semantics | Reject it and preserve correctness over a smaller metric. | ## Examples Use a compact handoff that makes scope, mutation authority, and verification evidence reviewable. Input: ```text requests-hour=1800; complexity-hour=1200000; polling=60s; freshness-slo=5m ``` Expected handoff: ```text push-candidates=identified; budget=headroom-set; price-claim=none ``` ## 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)
© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace