A task-triage tool that reviews each task in a software plan and recommends whether an agent can do it alone, should pause for a human check, or should leave the implementation to a person.

Use it to score planned tasks, identify risky or unfamiliar work, and save the resulting decisions for the implementation workflow.

It helps teams decide where human review is needed instead of applying the same level of trust to every task.

adev:route — Skill by agentic-development

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/agentic-development/adev-plugin/route

Any agent

npx skills add agentic-development/adev-plugin --skill route

Clone the repo

git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,384 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00092	$0.04384
Opus 5	$0.00046	$0.02192
Sonnet 5	$0.00018	$0.00877
Haiku 4.5	$0.00009	$0.00438

Measured 2d ago against content hash e2900a69d733, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:route 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 2d 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.

providers/codex/skills/route/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Routing Advisor

Score each task in an implementation plan on four dimensions and recommend a routing mode: auto-agent (fully autonomous), assisted-agent (checkpoint at mid-point), or human-only (agent scaffolds, human implements). Decisions are persisted to the sibling <plan-stem>.routing.json sidecar — never into the plan body — and /adev:implement reads them from there to adjust execution behavior per task.

Announce at start: "I'm using the adev:route skill to score tasks and recommend routing."

Arguments

--plan <path>: route all tasks in a plan file (required unless --task is used)
--task <N>: route a specific task number from the plan (requires --plan)
--dry-run: show scores and recommendations without writing the <plan-stem>.routing.json sidecar

Prerequisites

The plan file must exist and follow the format produced by /adev:plan. If the plan does not exist, suggest running /adev:plan --spec <path> first.

Step 1: Load Context

Read the following files. Each informs the scoring decisions that follow.

The plan file: Read the plan at the path provided by --plan. Extract the list of tasks, their file targets, specialist tags, charter capability references, and dependency chains.
The spec: Read the Live Spec referenced in the plan header. Extract acceptance criteria, behavioral contracts, and error cases. The completeness of these elements feeds Dimension 1.
Constitution: Read .context-index/constitution.md. Extract architecture boundaries and non-negotiable principles. These inform blast radius assessment.
Manifest (specialists registry): Read .context-index/manifest.yaml. Note the specialists section and their trigger patterns. Specialist availability can improve pattern coverage scores.
Golden samples: Read .context-index/samples/ directory listing. For each sample, note its filename and the pattern it represents. Sample availability directly feeds Dimension 2.
Boundary rules: If .context-index/governance/boundaries.yaml exists, read it. Boundary crossings increase blast radius scores.

Read the full file on GitHub · 300 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.

agents/openai.yaml 188 B

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.

2d ago First seen · 300 lines · 92 tokens per session scan A e2900a69d733

Subscribe to this mod's changes

adev:route is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 4,384 once invoked, about $0.0005 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 2026-08-30.

Code review Planning Testing

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens