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 skills add smileynet/teach-me --skill serve-workspacegit clone --depth 1 https://github.com/smileynet/teach-meWrote 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/smileynet/teach-me/serve-workspace)<a href="https://agentmods.dev/skills/smileynet/teach-me/serve-workspace"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/serve-workspace/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/smileynet/teach-me/serve-workspace"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/serve-workspace.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00087 | $0.01377 |
| Opus 5 | $0.00044 | $0.00688 |
| Sonnet 5 | $0.00017 | $0.00275 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade B, and why
serve-workspace scanned grade B with 2 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 9d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
**PowerShell gotcha:** inline `curl -d '{"status":"complete"}'` gets mangled. Use a file: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: "Run and manage teach-me's serve.py — start ONE server in the background (LAN-ready), poll readiness, hit the /api/map status endpoints, and stop cleanly. Trigger: serve, start the server, run serve.py, back How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serve Workspace
Run serve.py (the FastAPI generation + map server that mounts a workspace at / and
project /assets) correctly from agent context. The launcher tools/serve-bg.py owns the
process logic; this skill is the decision layer + the API contract.
Which command (decision table)
| Goal | Command | Notes |
|---|---|---|
| Start a server for a task (default) | mise run serve:bg -- [--workspace P] [--lan] [--port N] |
Non-blocking; returns when ready, prints URLs, records PID. Use this in any tool call. |
| Stop it | mise run serve:stop (or serve:bg -- --stop) |
Kills by PID file, cross-platform. |
| Is it up? | python tools/serve-bg.py --status |
Reports PID + port state. |
| Restart (replace) | mise run serve:restart -- [...] |
--force: stops the existing one, starts fresh. |
| Interactive human session | mise run serve / serve:lan |
Blocking — never in an agent tool call. |
| Live-reload during code edits | mise run serve:dev |
Blocking; auto-reloads on tools/ changes. |
The non-blocking rule (#1 trap)
serve, serve:lan, and raw uvicorn.run block forever — calling them in a shell
tool wastes the whole call on a timeout. For any agent-initiated server, use serve:bg.
It spawns detached (Windows creationflags, Unix setsid) per the Windows steering — do
NOT hand-roll Start-Process -RedirectStandard*/-NoNewWindow (those block; see
project-conventions/references/windows.md).
Only ONE server at a time (enforced)
serve:bg refuses to start a second server:
- If a background server WE started is already alive (tracked via
.scratch/serve-bg.pid, on any port) → refused. Use--stop, or--forceto replace it. - If the target
--portis held by a different process (a foregroundserve, a stray listener) → refused; it never clobbers something it doesn't own. Stop that process or pick another--port.
To guarantee a clean single instance: mise run serve:restart -- [...] (force-replace) or
serve:stop then serve:bg.
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.
- 9d ago First seen · 99 lines · 87 tokens per session scan B 9967ed8edd35
serve-workspace is a skill published in the GitHub repository smileynet/teach-me (3 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,377 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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
anki
Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
textbook-distillation
Turn a textbook or long-form source into a self-paced learning track: chapter map, lesson plan, then self-contained HTML lecture notes (styled as the human specifies) with worked examples, exercises, and checkpoint questions. Read this for "lecture notes" / "study notes" / "course" / "syllabus" requests from a…
learning-notes-automation
A workflow for turning videos, podcasts, and articles into structured learning notes. It extracts key ideas and creates flashcards that can be imported into Anki, a spaced-repetition study app.
antivibe
Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.
learning-agility
Builds the leader's capacity for rapid, continuous learning through humility, curiosity, feedback receptivity, cross-training, reflective practice, and deliberate skill selection. Use when a leader's expertise has become stale, when the organisation faces skills gaps that training alone cannot close, when setbacks…