Agent-Harness-Kit: Skill for Claude Code

.agents/skills/request-router/SKILL.md

request-router is a skill for Claude Code, Codex from Eduardo-Salvador/Agent-Harness-Kit. It costs 35 tokens per session (294 once invoked), scanned A, original, MIT.

A request classifier that places each task into one of four work modes before the project workflow begins.

In plain words
What is it for?
It classifies requests, applies explicit overrides and hard triggers, and rechecks the choice when the work grows or verification fails.
Why use it?
It prevents every request from going through the same process and promotes quick work when the task is small, while sending uncertain or risky work through the full process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Eduardo-Salvador/Agent-Harness-Kit's own configuration. It tells Claude Code and Codex how to work on Agent-Harness-Kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Agent-Harness-Kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.agents/skills/request-router/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-Kit

Made for: Claude Code, Codex.

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.

agentmods badge for request-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/request-router/github.svg)](https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/request-router)
Your own site
<a href="https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/request-router"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/request-router/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.

agentmods 80×15 button for request-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/request-router"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/request-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00294
Opus 5 $0.00017 $0.00147
Sonnet 5 $0.00007 $0.00059
Haiku 4.5 $0.00003 $0.00029

Measured 5d ago against content hash 67c7fe5474ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

request-router 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 5d 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.

.agents/skills/request-router/SKILL.md · 14 lines

What it actually says

Request router

  1. Before mutating work or Harness ceremony, read ../../../harness/playbooks/request-routing.md and ../../../docs/ADAPTIVE-EXECUTION.md. Read-only audit/diagnosis does not trigger first-run.
  2. Explicit full wins. Otherwise use full for two or more real agents, a human loop, required audit, insufficient model capability, or unresolved consequential ambiguity. Actual security/privacy/authorization/destructive changes require full audit; API/dependency keywords alone are not triggers.
  3. Classify deterministically first. Use an available economical AI classifier only when ambiguity remains and classification is cheaper than the work. Do not call a separate provider, invent credentials, hardcode a model ID, or claim a silent model switch.
  4. Route to exactly one lane and independently assign assurance: none|light|full. Unresolved consequential ambiguity selects full-harness; ordinary uncertainty may be resolved by bounded inspection.
  5. For vibe, permit a small local behavior change in one workstream with no Harness artifacts or mandatory RED, but require a focused deterministic check.
  6. Re-evaluate scope before further edits. Failed verification starts bounded in-scope recovery; promote only when a full-Harness condition is discovered.
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. 5d ago Changed 67c7fe5474ac
  2. 10d ago First seen · 14 lines · 35 tokens per session scan A 8937a0ad86d1

Subscribe to this mod's changes

request-router is a skill published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 294 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

qa

Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…

arcee-ai/nac · 100 tokens

release

Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.

arcee-ai/nac · 53 tokens

openrig-user

Use when a specific rig command, subcommand, or flag is already known and you need its exact syntax, JSON shape, defaults, or error meaning. NOT for natural capability discovery, open-ended how-do-I questions, or choosing which OpenRig move applies.

mvschwarz/openrig · 58 tokens

triage

Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…

arcee-ai/nac · 65 tokens

orienting-to-an-inherited-seat

Use when you have just been primed into an EXISTING seat through a planned handover — a different agent retired and handed you the seat plus its earned context — and you need a world model of what just happened to you. Covers how a handover differs from compaction and from a fresh launch, the…

mvschwarz/openrig · 207 tokens

forming-an-openrig-mental-model

Use when the system around you does not make sense yet: you just booted into a seat and do not know how the pieces fit; someone said rig, pod, seat, fleet, topology, or slice and you are not certain what they mean here; you are unsure what kind of rig you are in or what it is for; you do not know how skills reach you…

mvschwarz/openrig · 117 tokens