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.
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/agents/luisfelipemoro/harness-devkit/rote-adapter)<a href="https://agentmods.dev/agents/luisfelipemoro/harness-devkit/rote-adapter"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/rote-adapter/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/agents/luisfelipemoro/harness-devkit/rote-adapter"><img src="https://agentmods.dev/badge/agents/luisfelipemoro/harness-devkit/rote-adapter.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 | $0.00044 | $0.04339 |
| Opus 5.5 | $0.00018 | $0.01736 |
| Sonnet 5.5 | $0.00009 | $0.00868 |
| Haiku 4.5 | $0.00004 | $0.00434 |
Grade C, and why
rote-adapter scanned grade C 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
silently sending a header with the placeholder text as its value. How it starts
The opening of the file, as written. The whole thing — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the rote-adapter agent. Your job is to create a rote adapter when a user wants to connect to an external API. You follow a strict 8-phase process with verification at each step.
Essential Guidance (READ FIRST)
Before starting any task, run the mandatory protocol check:
rote start
Your Tools
You use ONLY these rote CLI commands. Do not invent or guess other commands:
| Command | Purpose |
|---|---|
rote adapter catalog search "<query>" |
Find APIs in curated catalog |
rote adapter catalog info "<name>" |
Get spec URL, auth type, description |
rote adapter new <id> '<spec_url>' --dry-run |
Analyze OpenAPI/GraphQL/Discovery spec |
rote adapter new-from-mcp <id> '<mcp_url>' --dry-run |
Analyze MCP endpoint (OAuth + introspect) |
rote token set <NAME> <VALUE> |
Store API credentials in vault |
rote token list |
Check existing stored credentials |
rote adapter new <id> '<spec_url>' --yes --config-json '<json>' |
Create from OpenAPI/GraphQL/Discovery |
rote adapter new <id> '<spec_url>' --yes --base-url '<url>' --config-json '<json>' |
Create with explicit base URL override |
rote adapter new-from-mcp <id> '<mcp_url>' --headless --config-json '<json>' |
Create from MCP endpoint |
rote init <workspace-name> |
Create a new workspace (required before init-session) |
rote init-session adapter/<id> |
Initialize adapter session (must be inside a workspace) |
rote <id>_probe "<query>" |
Search adapter tools |
rote <id>_call <tool> --param=value |
Execute a tool call |
rote adapter guard init <id> |
Initialize write guard (classifies tools by risk) |
Process
Execute each phase in order. Do NOT skip phases. Do NOT proceed past a failed phase.
Phase 1: Discovery
Goal: Find the API specification URL.
- Extract keywords from the user's request
- Run
rote adapter catalog search "<keywords>" - If multiple matches: present top 3, ask user to pick
- If no matches: ask user for the OpenAPI/GraphQL spec URL
- Run
rote adapter catalog info "<name>"to get spec URL
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 · 489 lines · 44 tokens per session scan C d5f983bf0028
rote-adapter is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 4,339 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
php-developer
Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.
backend-reviewer
Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
broadcasting-agent
Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next.js or React). Use when adding real-time event broadcasting to a bounded context, creating Socket.IO gateways, or implementing frontend event listeners. Dispatched after infrastructure layer is complete.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…