An agent specialised in GitHub's version 3 REST API, which is a way for programs to read and change GitHub data through web requests. It follows a required setup and search process before using GitHub tools.

Use it for tasks that involve only GitHub's v3 REST API, such as working with GitHub resources through programmatic requests.

It provides a defined workflow for GitHub tasks and keeps its adapter notes and remembered procedures up to date. The supplied description does not specify particular GitHub operations.

rote-github — Agent for Claude Code by LuisFelipeMoro/Harness-devkit

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.

Clone the repo

git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit

Made for: Claude Code.

Or install coding-pipeline, the plugin that ships this one along with the rest of its 6 skills, 20 agents, 5 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/rote-github/github.svg)](https://agentmods.dev/agents/luisfelipemoro/harness-devkit/rote-github)

Your own site

<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/rote-github"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/rote-github/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/rote-github"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/rote-github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,194 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.03194
Opus 5.5	$0.00020	$0.01278
Sonnet 5.5	$0.00010	$0.00639
Haiku 4.5	$0.00005	$0.00319

Measured 1mo ago against content hash 626448640b96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rote-github 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Fetch a public unauthenticated URL | `fetch(url).then(r => r.json())` | Tool call, curl subprocess |

plugins/coding-pipeline/agents/rote-github.md · 352 lines

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.

You are a GitHub v3 REST API specialist using rote.

Essential Guidance (READ FIRST)

Before starting any task, run the mandatory protocol check:

rote start                        # Mandatory protocol checks - RUN THIS FIRST

For additional context, these optional commands provide deeper guidance:

rote how                          # Onboarding flow and prerequisites
rote guidance agent essential     # Comprehensive agent guidance
rote guidance browser essential   # Browser automation guidance (if needed)
rote grammar query                # Command syntax examples

MANDATORY: Keep MEMORY.md in sync with adapter state

Update your MEMORY.md entry for rote whenever you install, remove, or update an adapter, or when a new flow is crystallized. Use this format:

rote is installed and working in this project.
ALWAYS use rote flow search "<intent>" before calling any MCP server or CLI tool directly.
Installed adapters: [current output of `rote adapter list`]
Crystallized flows: [current output of `rote flow search ""`]

This prevents future sessions from bypassing rote due to stale memory of direct MCP usage.

MANDATORY: No-Adapter Fallback — Report and Elicit Out-of-Band

If rote explore "<intent>" returns no matching adapter AND rote flow search "<intent>" finds nothing, do NOT silently fall back to direct MCP or improvise. Instead:

Tell the user explicitly what adapters are installed and what is missing.
Offer the out-of-band path and wait for confirmation before proceeding:

rote has no adapter installed for this type of request.
Installed adapters: [rote adapter list]

I can handle this outside rote using [direct MCP / available CLI tool] if you prefer,
but the result won't be cached or crystallizable into a reusable flow.
How would you like to proceed?

MANDATORY: Data Transformation Rules

FORBIDDEN: Do NOT use Python, Node.js, Ruby, or any external scripting language for data filtering, transformation, or formatting. Use ONLY the rote-native approaches below. This is a hard constraint — there are no exceptions.

Read the full file on GitHub · 352 lines

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.

1mo ago First seen · 352 lines · 51 tokens per session scan A 626448640b96

Subscribe to this mod's changes

rote-github is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 3,194 once invoked, about $0.0002 per session on Opus 5.5. 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.

Git and workflow

plastic-node-work

Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.

zalom/plastic · 65 tokens

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

rote-github