rote

A routing and reuse layer for MCP servers and command-line tools. MCP servers are tools that let an agent work with external services or data, while rote records reusable workflows for them.

In plain words
What is it for?
Use it before directly calling an MCP server or CLI to inspect available adapters, search for a matching workflow, or create a reusable flow from a successful operation.
Why use it?
It reduces repeated tool setup and calls by checking for existing workflows, caching responses, and reusing successful operations.

Skill for Claude CodeCodex

Part of the devtools plugin — 8 skills shipped together

Install

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.

agentmods
npx agentmods add skills/luisfelipemoro/harness-devkit/rote
Any agent
npx skills add LuisFelipeMoro/Harness-devkit --skill rote
Clone the repo
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit

Made for: Claude Code, Codex.

Or install devtools, the plugin that ships this one along with the rest of its 8 skills.

Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 866 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00118 $0.00866
Opus 5 $0.00059 $0.00433
Sonnet 5 $0.00024 $0.00173
Haiku 4.5 $0.00012 $0.00087

Measured 3d ago against content hash 4b6822e243ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rote 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.

If `rote flow search` and `rote explore "<intent>"` both come up empty, check the installable catalog before any WebFetch/curl/direct MCP, using the `rote adapter catalog search` / `catalog info` / `adapter new` / `<id>_
plugins/devtools/skills/rote/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude and the rote CLI are a pair: Claude discovers + executes via the skill; the CLI crystallizes + replays. Every successful Claude operation becomes a reusable CLI flow. Every CLI-crystallized flow is available to Claude on next invocation.

Command syntax and templates live in references/rote-reference.md; this body is the router. Never cat, ls, or hand-edit files under ~/.rote/ — always use the rote commands listed under "State inspection" below.

Phase 0 — State Snapshot (always runs at skill invocation)

Before any other step, establish what rote knows right now: run rote adapter list and rote flow search "", then emit a compact ≤5-line inventory of adapters and flows (format in references/rote-reference.md). If rote is not installed (command not found), tell the user to install it and stop.

Rule 1 — Search flows FIRST, always

Before calling any MCP server or CLI tool directly, run rote flow search "<your intent>". Flow found → run it from /tmp (keeps you outside ~/.rote/workspaces/) using the shell or rote deno run commands in references/rote-reference.md. No flow → proceed to Rule 2.

Rule 2 — Check catalog before falling back out-of-band

If rote flow search and rote explore "<intent>" both come up empty, check the installable catalog before any WebFetch/curl/direct MCP, using the rote adapter catalog search / catalog info / adapter new / <id>_probe / <id>_call sequence in references/rote-reference.md. If catalog has nothing → tell the user explicitly and wait for confirmation before falling back out-of-band.

Do not retry discovery after a hit. A result from catalog search means advance to catalog info or adapter new — not another search.

Rule 3 — Crystallize every successful operation

After any successful adapter call that was NOT already run from a flow, crystallize it with rote flow crystallize then rote flow release (full syntax and the <adapter>-<verb>-<noun> name format in references/rote-reference.md) so the CLI can replay it. This is what makes the CLI and skill a pair. Skip crystallization only when the operation is destructive, one-off, or parameterized in a way that makes reuse meaningless.

Read the full file on GitHub · 50 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 50 lines · 118 tokens per session scan A 4b6822e243ee

Subscribe to this mod's changes

rote is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 866 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens