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/coefficient-work/mcp-doctor/tars-remote-apinpx skills add Coefficient-work/mcp-doctor --skill tars-remote-apigit clone --depth 1 https://github.com/Coefficient-work/mcp-doctorWrote 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/coefficient-work/mcp-doctor/tars-remote-api)<a href="https://agentmods.dev/skills/coefficient-work/mcp-doctor/tars-remote-api"><img src="https://agentmods.dev/badge/skills/coefficient-work/mcp-doctor/tars-remote-api.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 | $0.00091 | $0.02810 |
| Opus 5 | $0.00046 | $0.01405 |
| Sonnet 5 | $0.00018 | $0.00562 |
| Haiku 4.5 | $0.00009 | $0.00281 |
Grade A, and why
tars-remote-api scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Re-implement Google auth or “temporary” local Gmail scripts in jobs-foundation etc. | Preflight + `curl` / `tars-remote.sh` | How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TARS remote API — agent skill
Hard rule (read first)
For Louis’s Gmail, Miriam’s (Mim’s) Gmail, or Google Drive / Sheets / Docs in household, business, or ops context:
- Always use this skill → Mac mini
:3049remote API. - Do not use Cursor MCP plugins
plugin-gmail-gmailorplugin-google-drive-google-driveas the first choice (or as a fallback when TARS is available). - Do not set up local Google OAuth, service-account JSON, or refresh tokens in project repos.
- Do not invent alternate Google auth paths “because this isn’t the TARS repo.”
If preflight fails, stop and report the printed fix — do not silently switch to plugins or claim “Gmail isn’t authenticated.”
When to use
- Any Gmail search, read, draft, or label/modify for Louis or Mim
- Google Drive file search; Sheets get/update/append; Docs get/batchUpdate
- User mentions TARS, Mac mini,
:3049, cross-repo Google, Antagning/LU (Mim), or household Drive - Errors:
REID_REMOTE_TOKEN not set,401 Unauthorized, or agent temptation to open Gmail/Drive plugins
Anti-patterns
| Don’t | Do instead |
|---|---|
Call plugin-gmail-* / plugin-google-drive-* for Louis/Mim/ops mail or Drive |
tars-remote-api + :3049 |
Copy OAuth client secrets / refresh tokens into a project .env |
OAuth stays on Mac mini (~/openclaw/.env) only |
| Re-implement Google auth or “temporary” local Gmail scripts in jobs-foundation etc. | Preflight + curl / tars-remote.sh |
| Guess “not authenticated” without running preflight | Run preflight; quote its failure message |
| Default Mim mail to Louis’s mailbox | Pass "account":"mim" (or Mim mailbox alias) |
| Assume Drive works for Mim | Drive/Sheets/Docs are Louis only; Mim is Gmail-only |
Prerequisites (Cursor secrets — set once)
Add in Cursor Settings → Cloud Agents → Secrets (cursor.com/docs/cloud-agent/setup). Secrets are account/workspace-scoped, not per-repo.
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.
- 3d ago First seen · 239 lines · 91 tokens per session scan A 8829289a4d89
tars-remote-api is a skill published in the GitHub repository Coefficient-work/mcp-doctor (0 stars, last pushed 10d ago), licensed MIT. It adds 91 tokens to every session and 2,810 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…