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/stevekinney/temporal-mcp/skillnpx skills add stevekinney/temporal-mcp --skill skillgit clone --depth 1 https://github.com/stevekinney/temporal-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/stevekinney/temporal-mcp/skill)<a href="https://agentmods.dev/skills/stevekinney/temporal-mcp/skill"><img src="https://agentmods.dev/badge/skills/stevekinney/temporal-mcp/skill.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00147 | $0.02766 |
| Opus 5 | $0.00073 | $0.01383 |
| Sonnet 5 | $0.00029 | $0.00553 |
| Haiku 4.5 | $0.00015 | $0.00277 |
Grade A, and why
temporal-mcp 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 4d ago.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill provides curated Temporal development knowledge through a set of reference files covering determinism, patterns, gotchas, versioning, troubleshooting, error handling, and language-specific guidance for TypeScript, Python, and Go. The knowledge layer is standalone and useful without any running infrastructure. Alongside it, the temporal-mcp MCP server connects to a live Temporal cluster and exposes 28 read-only tools for inspecting workflow state, task queues, schedules, namespaces, and worker deployments in real time. The two layers are synergistic: references explain what the code should do, and the MCP tools reveal what is actually happening in production.
How temporal-mcp Fits
The temporal-mcp MCP server connects to the Temporal cluster's Frontend gRPC service as a read-only observer. It can inspect workflows, task queues, schedules, namespaces, and worker deployments, but it never starts, signals, cancels, or terminates workflows (the one exception: triggering an already-configured schedule). All mutation happens through your application's Temporal client and workers.
History Replay: Why Determinism Matters
Temporal rebuilds workflow state by re-executing the workflow function against its recorded event history every time a worker picks up a Workflow Task. The SDK replays past commands without re-executing the underlying work (activities, timers), then resumes at the point where new work needs to happen. Every execution of the workflow function must produce the exact same sequence of commands for the same history — this is the determinism contract. Non-deterministic code (random numbers, wall-clock time, direct I/O, non-deterministic iteration order) causes replay to produce a different sequence of commands than what was recorded, which the SDK detects and surfaces as a non-determinism error, crashing the workflow. See references/core/determinism.md for the full breakdown of what breaks replay and how to fix it.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/core/determinism.md 7.8 KB
- references/core/error-reference.md 8.7 KB
- references/core/gotchas.md 11 KB
- references/core/operational-patterns.md 11 KB
- references/core/patterns.md 13 KB
- references/core/schedules.md 7.0 KB
- references/core/troubleshooting.md 8.9 KB
- references/core/versioning.md 7.6 KB
- references/go/determinism.md 4.3 KB
- references/go/go.md 5.1 KB
- references/go/gotchas.md 6.5 KB
- references/go/patterns.md 6.9 KB
- references/go/versioning.md 5.9 KB
- references/python/determinism.md 5.6 KB
- references/python/gotchas.md 6.3 KB
- references/python/patterns.md 7.2 KB
- references/python/python.md 5.1 KB
- references/python/versioning.md 5.4 KB
- references/typescript/determinism.md 5.7 KB
- references/typescript/gotchas.md 6.4 KB
- references/typescript/patterns.md 6.3 KB
- references/typescript/typescript.md 4.6 KB
- references/typescript/versioning.md 4.1 KB
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.
- 4d ago First seen · 191 lines · 147 tokens per session scan A ce62cca2b644
temporal-mcp is a skill published in the GitHub repository stevekinney/temporal-mcp (5 stars, last pushed 8d ago), licensed MIT. It adds 147 tokens to every session and 2,766 once invoked, about $0.0007 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…