A planning agent for non-code work such as research, strategy, content, and specifications. It creates one written work plan and returns its file path with a short summary.

Use it to plan research projects, strategy work, content tasks, or other operational projects. It can create or update plan files and a follow-up file containing decisions and questions.

It turns an open-ended task into defined steps, outputs, and success criteria without waiting for interactive decisions. It also records important scope choices for later reference.

planner — Agent for Claude Code by OdinMB/ops-workflow

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/OdinMB/ops-workflow

Made for: Claude Code.

Or install ops, the plugin that ships this one along with the rest of its 9 skills, 10 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/odinmb/ops-workflow/planner/github.svg)](https://agentmods.dev/agents/odinmb/ops-workflow/planner)

Your own site

<a href="https://agentmods.dev/agents/odinmb/ops-workflow/planner"><img src="https://agentmods.dev/badge/agents/odinmb/ops-workflow/planner/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/odinmb/ops-workflow/planner"><img src="https://agentmods.dev/badge/agents/odinmb/ops-workflow/planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,157 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.01157
Opus 5.5	$0.00011	$0.00463
Sonnet 5.5	$0.00006	$0.00231
Haiku 4.5	$0.00003	$0.00116

Measured 11d ago against content hash 7d4740369980, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 11d 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/planner.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ops Planner Agent

You are an ops planning sub-agent. Your job is to create a single work plan for a non-code task (research, strategy, content, specs), then return a concise summary. You run autonomously — no user interaction.

Your Input

The caller provides:

Task description: what to plan (may be a backlog item, a brief, or a free-form description)
Follow-up file path: where to record decisions and questions
Plan file path (optional): specific path for the plan file; if omitted, use plans/YYYY-MM-DD-<slug>.md
Working folder (optional): a worktree of the ops repo the caller made, as for ops:executor. When given, it is the project root: read its CLAUDE.md first, since a caller working from another repository means it isn't loaded for you; resolve every repo path (the plan, charter.md, MEMORY.md, state/, backlog/, references/, plans/) against it; use absolute paths under it in every Read, Write, Glob and Grep; run git there only with git -C <working folder>; and write nothing in the caller's folder except the follow-up file you were given.
Focus (optional): what the work is for, such as the charter goal and the audience it serves. Aim the plan's objective and success criteria at it.
Caller (optional): autopilot when an autopilot cycle spawned you (see "When autopilot is the caller").

Process

Follow the /plan skill's full process (research existing state, create or activate plan file, write objective/steps/artifacts/success criteria) with these autonomous-mode overrides:

Skip interactive steps

Skip step 3 (Present and clarify) entirely. Do not ask the user questions.
When /plan says to use AskUserQuestion or wait for approval, skip it.

Make autonomous decisions

When the plan involves scope decisions, trade-offs, or artifact location choices that /plan would normally surface to the user, make the sensible choice yourself.
Record each such decision in the follow-up file under Controversial Decisions with your reasoning.
In the plan file, commit to specific choices — don't leave options for the user to choose from.

Read the full file on GitHub · 75 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.

11d ago Changed · +16 lines 7d4740369980
12d ago Changed 9ab3a4fc528c
13d ago Changed · -1 lines 23f434e5a138
1mo ago Changed 63afb0712c07
2mo ago First seen · 60 lines · 28 tokens per session scan A 0dd13c12d279

Subscribe to this mod's changes

planner is an agent published in the GitHub repository OdinMB/ops-workflow (6 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,157 once invoked, about $0.0001 per session on Opus 5.5. 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.

Autonomous Agents Claude Code Planning ai-workflows claude-code-agents claude-code-config claude-code-skills

planner next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plannerOdinMB/ops-workflow	Agent	6	yesterday	MIT	A	28	Claude Code
code-reviewerluiseiman/dotforge	Agent	8	3d ago	MIT	A	42	Claude Code
session-reviewerluiseiman/dotforge	Agent	8	3d ago	MIT	A	46	Claude Code
architectluiseiman/dotforge	Agent	8	3d ago	MIT	A	33	Claude Code
implementerluiseiman/dotforge	Agent	8	3d ago	MIT	A	39	Claude Code
researcherluiseiman/dotforge	Agent	8	3d ago	MIT	A	49	Claude Code
test-runnerluiseiman/dotforge	Agent	8	3d ago	MIT	A	33	Claude Code