Loom is a delivery harness that guides coding agents through defining, planning, implementing, checking, repairing, previewing, and handing off software changes. It is used with Claude Code, Codex, OpenCode, and other coding agents when work must be continued or inspected across sessions. The catalogue skills, hooks, commands, instructions, and plugin extend or operate this workflow.
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 valkor-ai/loom --skill mcp-drivergit clone --depth 1 https://github.com/valkor-ai/loomWrote 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/valkor-ai/loom/mcp-driver)<a href="https://agentmods.dev/skills/valkor-ai/loom/mcp-driver"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/mcp-driver/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/valkor-ai/loom/mcp-driver"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/mcp-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00171 | $0.01110 |
| Opus 5.5 | $0.00068 | $0.00444 |
| Sonnet 5.5 | $0.00034 | $0.00222 |
| Haiku 4.5 | $0.00017 | $0.00111 |
Grade A, and why
mcp-driver 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Driver — Runtime Debug & Inspection
$ARGUMENTS
When to use this skill
MCP is the upgrade path when faster tools hit a wall. The fast loop handles most issues:
| Problem type | Fast path (no MCP) |
|---|---|
| Syntax / parse error | headless-build |
| Unit test failure | gdunit-driver |
| API lookup | godot-api |
Escalate to MCP when:
- Compile-pass / runtime-fail — headless-build says OK but something is wrong when the game actually runs
- Test-pass / behavior-wrong — unit tests pass but the game does not behave correctly in practice
- Visual issue — screen is black, sprites missing, z-order wrong, camera not following
- Input not working — keys/mouse/gamepad produce no response at runtime
- Physics misbehavior at runtime — objects pass through each other, wrong gravity, jittery movement
- Need live state — want to see the actual node tree, console output, or runtime errors
- Repeated headless failure — a fix has been attempted 2+ times via headless path without success
If none of these apply, use the fast path skill instead.
Debug-fix loop (overview)
When you escalate to MCP, follow this loop. Max 3 iterations before asking the user for help.
1. RUN — run_project (optionally with a specific scene)
2. CAPTURE — get_debug_output → collect errors, warnings, prints
3. ANALYZE — parse output, identify root cause
4. FIX — modify code / scene / config to address the issue
5. VERIFY — stop_project → run_project again, get_debug_output
6. REPORT — summarize what was wrong, what was changed, and the outcome
Each step is detailed in references/workflow.md. Common runtime issue patterns are in references/debug-patterns.md.
Project path
MCP tools require a projectPath parameter — the directory containing project.godot. Determine it from the current working directory or ask the user if ambiguous:
# Quick check
ls project.godot 2>/dev/null && echo "Project root: $(pwd)"
What ships with it
3 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.
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.
- 1mo ago First seen · 122 lines · 171 tokens per session scan A 37bf98463398
mcp-driver is a skill published in the GitHub repository valkor-ai/loom (1,271 stars, last pushed 2d ago), licensed Apache-2.0. It adds 171 tokens to every session and 1,110 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
performance-optimization
Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each…
unity-console
Capture and query the Unity Editor console.
diagnosing-bgs-problems
A symptom-first guide for investigating crashes, frame-rate drops, stuttering, freezes, and startup failures in Bethesda Game Studios games with mods.
axiom-audit-spritekit
Use when the user wants to audit SpriteKit game code for common issues — physics bitmask issues, draw call waste, node accumulation, and action leaks.