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 skills/ch-raph/linear-cache-mcp/linear-opsnpx skills add ch-raph/linear-cache-mcp --skill linear-opsgit clone --depth 1 https://github.com/ch-raph/linear-cache-mcpWhat 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 | $0.00042 | $0.00771 |
| Opus 5 | $0.00021 | $0.00385 |
| Sonnet 5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
linear-ops 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 yesterday.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linear Ops Skill
Purpose
Use this skill whenever a task mentions Linear, issues, projects, backlog, meeting-note triage, labels, statuses, or MCP/API rate limits.
Mandatory protocol
- Check local cache status first. Read
.agent/linear-cache/manifest.jsonor uselinear_cache_statuswhen available. - Use cache-first tools for broad reads. Prefer
linear_cache_search_issues,linear_cache_list_projects, and local.agent/linear-cache/latest/*.jsonover direct broad Linear MCP calls. - Never write from cache alone. Before creating/updating/commenting/moving Linear entities, live-fetch exact target entities through the cache MCP write tool or direct Linear tool if the cache MCP is unavailable.
- Patch/write through after mutations. After Linear writes, update local cache and request ledger, or note explicitly if this was not possible.
- Check budget before broad syncs. Use
linear_cache_budget_statusor local request ledger counts. If above soft budget, avoid nonessential broad scans. - Linear remains source of truth. If live state conflicts with cache, trust live state and patch/flag the cache.
Request budget discipline
Cache MCP tool names use underscores for MCP client compatibility, for example linear_cache_status rather than linear_cache.status.
Suggested hourly thresholds:
< 900/hour: normal mode.900-1200/hour: avoid broad refreshes; prefer targeted fetches.1200-1400/hour: targeted reads/writes only.> 1400/hour: ask user before nonessential Linear calls.
Budget checks should use local ledger data, not Linear API calls.
Project workflow template
Customize this section per project.
Recommended defaults:
- Use projects/docs for durable context, research, commitments, decision logs, and broad themes.
- Create issues only for bounded executable work with a clear owner/success condition.
- Use a decision-needed label/status for ambiguous or decision-bound work.
- Moving an issue to active work should require an owner and a one-sentence success condition.
- Avoid creating issues for pure context if a project update/document is more appropriate.
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.
- yesterday First seen · 72 lines · 42 tokens per session scan A c48068f37f4a
linear-ops is a skill published in the GitHub repository ch-raph/linear-cache-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 771 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.