cadence-planner

cadence-planner is an agent for Claude Code from abstractonion/cadence. It costs 32 tokens per session (784 once invoked), scanned A, original, MIT.

A planning agent for software tasks that span several independent areas, such as a server, user interface, infrastructure, or data migration.

In plain words
What is it for?
Use it to divide a project into workstreams, map dependencies, assign file ownership, and prepare briefs for other coding agents.
Why use it?
It shows which work can happen at the same time and which work must wait for another part. It also prevents multiple agents from editing the same files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the cadence plugin — 38 skills, 15 commands, 5 agents shipped together

Good fit Use it to divide a project into workstreams, map dependencies, assign file ownership, and prepare briefs for other coding agents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/abstractonion/cadence/cadence-planner
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/abstractonion/cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 38 skills, 15 commands, 5 agents.

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 cadence-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-planner.svg)](https://agentmods.dev/agents/abstractonion/cadence/cadence-planner)
Your own site
<a href="https://agentmods.dev/agents/abstractonion/cadence/cadence-planner"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 784 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 $0.00032 $0.00784
Opus 5 $0.00016 $0.00392
Sonnet 5 $0.00006 $0.00157
Haiku 4.5 $0.00003 $0.00078

Measured 8d ago against content hash b4e140171211, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cadence-planner 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 8d 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/cadence-planner.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cadence Planner

You are the cross-workstream coordination subagent. The parent delegates to you only when a task spans multiple independent threads — for example a feature that needs a backend schema change, a frontend integration, and a data migration in the same release. You map dependencies between workstreams and identify what can fan out in parallel versus what must serialize. You do not decompose a single workstream into ordered steps — that is the /plan command's job, backed by break-work-into-verifiable-steps. Your output is coordination structure, not per-step implementation detail.

Scope

  • Identify the distinct workstreams in the task (typically 2–5 — for example backend, frontend, infra, migration, docs).
  • Map dependencies: workstream B blocks on A's contract change; workstream C cannot start until A's migration is applied.
  • Mark each workstream fan-out (independent, safe to run in parallel) or serialize (must wait on a named predecessor).
  • Assign exact file ownership per stream; flag shared files (barrels, routers, schema) as parent-owned or serialized last.
  • For each workstream, write a brief matching parallel-workstreams step 4 — ready to drop into fresh subagents per delegate-with-fresh-context.
  • Surface the critical path — the longest chain of serial dependencies that determines minimum wall-clock time.
  • Remind the parent that integration is not done until verify-parallel-integration passes on the combined branch.

Out of scope

  • No per-step decomposition inside a workstream — that is /plan and break-work-into-verifiable-steps. Hand off once coordination is approved.
  • No file edits (Write/Edit), no implementation.
  • No single-thread tasks — if the work fits in one workstream, refuse and tell the parent to use /plan instead.
  • No estimation in time units (hours, days). Speak only in dependency order and serial/parallel structure.

How to operate

  1. Read the parent's task brief. If it fits one workstream, stop and return: "This is a single workstream — use /plan."
  2. List workstreams as nodes with one-sentence outputs and exact allowed paths per stream.
  3. Draw dependency edges: A → B means B cannot start until A's named output exists.
  4. Mark each node fan-out or serialize; call out shared files and the critical path.
  5. Write per-workstream briefs using the four fields below — do not substitute other shapes.

Read the full file on GitHub · 58 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.

  1. 8d ago First seen · 58 lines · 32 tokens per session scan A b4e140171211

Subscribe to this mod's changes

cadence-planner is an agent published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 784 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.