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 trevhud/rote --skill rote-compilegit clone --depth 1 https://github.com/trevhud/roteWrote 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/trevhud/rote/rote-compile)<a href="https://agentmods.dev/skills/trevhud/rote/rote-compile"><img src="https://agentmods.dev/badge/skills/trevhud/rote/rote-compile/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/trevhud/rote/rote-compile"><img src="https://agentmods.dev/badge/skills/trevhud/rote/rote-compile.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 | $0.00175 | $0.04147 |
| Opus 5.5 | $0.00070 | $0.01659 |
| Sonnet 5.5 | $0.00035 | $0.00829 |
| Haiku 4.5 | $0.00017 | $0.00415 |
Grade A, and why
rote-compile 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Compilation
You are the rote compiler. You read fuzzy AI skills and produce reliable workflows.
Input: a directory containing a SKILL.md and an optional references/
folder with sub-files.
Output: an intermediate representation (pipeline.yaml) plus
runtime-specific emitted code that the user can drop into their durable
execution engine. rote then renders a human-readable compilation report
(compile-report.md) from your pipeline.yaml and code: what was codified,
what stayed agentic, and every judgment call you marked.
The guiding philosophy: keep the LLM at points where the input is unbounded or ambiguous (parsing, classifying, drafting, summarizing). Codify everything else — control flow, retries, parallelism, idempotency, side-effecting tool calls, fixed batching — into deterministic code. Every token spent re-deriving a known-fixed procedure at runtime is waste.
Phase Routing
| Entry Point | Start At | Example Triggers |
|---|---|---|
| Full compilation | Phase 1 → 7 | "compile the bdr-outreach skill" |
| Report only | Phase 1 → 5, skip 6 | "analyze this skill, don't emit code" |
| Re-emit for different runtime | Phase 6 | "emit the existing pipeline.yaml for inngest" |
| Update compilation after skill changed | Phase 1 → 7, diff | "recompile bdr-outreach, it changed" |
Pipeline
Think in files, not in your head. Your reasoning is not a draft. Anything you would write out in full (the classification table, a module, a test) belongs in a file, written once. Reason about one decision at a time, just before the Write it informs. Do not plan the whole compile, or draft its files, in one long block of thinking first: a real compile spent 64,000 tokens and 14 minutes that way before its first Write, and the block was discarded when it hit the per-response output limit. So the order is:
- One turn of Reads: every rubric reference and every file of the source skill, together.
- Write
pipeline.yamlnext, before any module: it is the Phase 2 classification and the data flow in one artifact. Every module then takes exactly its node'sinputs:keys (andconstants:) as parameters, which is a check rote runs. - Write each module together with its test, two or three modules per turn.
eval.yaml, last. Then stop, and end your turn with one short sentence, not a summary: rote renderscompile-report.mdand prints the verdict, so a summary is output nobody reads.
What ships with it
8 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.
- 4d ago Changed · +19 lines 9500af3d48d3
- 5d ago Changed · +38 lines 9822c5cd3bd2
- 6d ago Changed · +29 lines 9bb34bc89a23
- 1mo ago First seen · 266 lines · 175 tokens per session scan A bdf4c3e39261
rote-compile is a skill published in the GitHub repository trevhud/rote (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 175 tokens to every session and 4,147 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 2026-08-31.
Other skills, from other repositories
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
explore
Explore the codebase and summarize how the project is wired.
watch
Open the Roundtable office in the browser — a live, read-only view of this machine's Claude Code sessions, with every subagent as a person at a desk and a timeline you can rewind.
gif
Turn this Claude Code session into a looping timelapse GIF of the Roundtable pixel office — every subagent as a person who walks in, works, reports and leaves. Writes one file in the working directory.
stats
Read every Claude Code transcript on this machine and report what they say about your own fan-out — how much of your output is written inside subagents, what a child costs before it starts, which hooks have ever fired. Read-only.
agent-goal-skill
Take a rough goal description and shape it into a polished, doctrine-compliant agent goal prompt. Output is for the user to copy/paste into Codex, Claude Code (native /goal), Droid, Auggie, or any CLI agent that benefits from a structured goal contract. The skill does NOT execute the goal — it shapes the prompt and…