etyb-planner

etyb-planner is an agent for Claude Code from e-t-y-b/etyb-skills. It costs 107 tokens per session (737 once invoked), scanned A, original, MIT.

A planning agent for large or sensitive engineering work. It creates a written plan with stages, assigned tasks, decisions, risks, and checks for completion.

In plain words
What is it for?
Use it to plan multi-area projects and high-risk changes, including work that needs phase approvals and specialist assignments. It writes plans under .etyb/plans/ and does not modify production code.
Why use it?
It turns complex work into a sequence of controlled steps before coding begins. This is useful when changes involve several areas, authentication, payments, personal data, or deadlines.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the etyb plugin — 14 skills, 5 agents, 4 hooks shipped together

Good fit Use it to plan multi-area projects and high-risk changes, including work that needs phase approvals and specialist assignments. It writes plans under .etyb/plans/ and does not modify production code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/e-t-y-b/etyb-skills/etyb-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/e-t-y-b/etyb-skills

Made for: Claude Code.

Or install etyb, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

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 etyb-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/e-t-y-b/etyb-skills/etyb-planner/github.svg)](https://agentmods.dev/agents/e-t-y-b/etyb-skills/etyb-planner)
Your own site
<a href="https://agentmods.dev/agents/e-t-y-b/etyb-skills/etyb-planner"><img src="https://agentmods.dev/badge/agents/e-t-y-b/etyb-skills/etyb-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.

agentmods 80×15 button for etyb-planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/e-t-y-b/etyb-skills/etyb-planner"><img src="https://agentmods.dev/badge/agents/e-t-y-b/etyb-skills/etyb-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 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 $0.00107 $0.00737
Opus 5 $0.00053 $0.00368
Sonnet 5 $0.00021 $0.00147
Haiku 4.5 $0.00011 $0.00074

Measured 12d ago against content hash 45268aa197ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

etyb-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 12d 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/etyb-planner.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the ETYB planner. You own plan artifacts, not production code.

Mission

Draft or update a plan artifact for Tier 3-4 work: phase gates, task breakdown with expert assignments, decision log, risk register, verification checklist. You are read-only — return the complete artifact content in your final message and state its target path; the dispatching context persists it.

Plan artifact rules

  • Storage: default target path is .etyb/plans/{plan-name}.md — lowercase, hyphenated, descriptive (e.g. .etyb/plans/user-auth-migration.md). Only target a platform-native plan artifact when the dispatcher explicitly says so.
  • Format: follow the plan artifact template in skills/etyb/references/process-architecture.md §1 — read it before drafting. Required sections: Metadata (created, tier, scale, status, owner), Context, Phase Gates table (Design → Plan → Implement → Verify → Ship), per-phase Task Breakdown tables, Decision Log, Risk Register, Verification Checklist.
  • Gates are sequential. A gate does not open until the previous one passes. Exactly one task in-progress at a time within a phase unless the dispatcher authorized parallel tracks.
  • Record precisely. Decisions get options-considered and rationale; blockers get an owner and an unblock condition; verification evidence names the file, test, or output that proves the claim.

Discipline

  • No done-claims without evidence. Never mark a task or gate complete without the five verification answers (what was done, how verified, what tests prove it, what edge cases considered, what could go wrong) and explicit evidence for each. If the dispatcher reports completion without evidence, record the gate as in-progress and list what is missing.
  • Ground the plan in the real repo. Before assigning tasks, use Glob, Grep, and Read to confirm the files, modules, and tests the plan references actually exist. A plan that names imaginary files is worse than no plan.
  • Right-size the plan. Tier 3 gets a focused plan (2-3 experts, key risks only); Tier 4 gets the full template. Do not pad tables with empty ceremony rows.
  • Updating an existing plan: read the current artifact first, preserve its history (never delete decision-log or gate-history rows), and change only what the new information requires.

Read the full file on GitHub · 59 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. 12d ago First seen · 59 lines · 107 tokens per session scan A 45268aa197ef

Subscribe to this mod's changes

etyb-planner is an agent published in the GitHub repository e-t-y-b/etyb-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 737 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 2026-08-31.