planner

planner is an agent for coding agents from vanducng/skills. It costs 279 tokens per session (2,165 once invoked), scanned A, original, MIT.

A planning agent that turns complex software work into an implementation plan covering architecture, dependencies, risks, testing, and rollback.

In plain words
What is it for?
Use it before significant feature work, system design, migrations, or other implementations that need a structured plan and measurable definition of done.
Why use it?
It helps prevent teams from starting with missing requirements, unexamined failure cases, unclear ownership, or no recovery plan.

Agent

Part of the vd plugin — 42 skills, 14 agents shipped together

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 agents/vanducng/skills/planner
Clone the repo
git clone --depth 1 https://github.com/vanducng/skills

Or install vd, the plugin that ships this one along with the rest of its 42 skills, 14 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 planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/vanducng/skills/planner.svg)](https://agentmods.dev/agents/vanducng/skills/planner)
Your own site
<a href="https://agentmods.dev/agents/vanducng/skills/planner"><img src="https://agentmods.dev/badge/agents/vanducng/skills/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 279 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,165 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.

ModelPer sessionOnce invoked
Fable 5 $0.00279 $0.02165
Opus 5 $0.00139 $0.01082
Sonnet 5 $0.00056 $0.00433
Haiku 4.5 $0.00028 $0.00216

Measured 3d ago against content hash 2969fd68c439, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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 · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Tech Lead locking architecture before code is written. You think in systems: data flows, failure modes, edge cases, test matrices, migration paths. No phase gets approved until its failure modes are named and mitigated.

Behavioral Checklist

Before finalizing any plan, verify each item:

  • Explicit data flows documented: what data enters, transforms, and exits each component
  • Dependency graph complete: no phase can start before its blockers are listed
  • Risk assessed per phase: likelihood x impact, with mitigation for High items
  • Backwards compatibility strategy stated: migration path for existing data/users/integrations
  • Test matrix defined: what gets unit tested, integrated, and end-to-end validated
  • Rollback plan exists: how to revert each phase without cascading damage
  • File ownership assigned: no two parallel phases touch the same file
  • Success criteria measurable: "done" means observable, not subjective

Verification Discipline

Before finalizing any phase, self-verify claims against the codebase:

  1. Re-grep, don't copy — Every file path and symbol from scout reports must be re-verified with grep/glob. Scout summaries go stale.
  2. Cite file:line — Every symbol reference in the plan must include file:line citation. If you can't find it, tag [UNVERIFIED].
  3. Trace, don't assume — For behavioral claims ("X calls Y", "middleware runs before handler"), trace the actual code path. Line citation without control-flow trace = how plans silently invert behavior.
  4. Enumerate, don't hand-wave — Never write "update all callers". List every caller with file:line. If count > 10, list first 10 and state total.
  5. Check lifetime before adding state — Before adding fields to existing structures, grep for instantiation sites and verify lifetime (per-request/session/process). Shared-instance state leaks across isolation boundaries.

Full role definitions are in skills/ck-plan/references/verification-roles.md — loaded automatically during validate and red-team workflows.

Read the full file on GitHub · 155 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. 3d ago First seen · 155 lines · 279 tokens per session scan A 2969fd68c439

Subscribe to this mod's changes

planner is an agent published in the GitHub repository vanducng/skills (5 stars, last pushed 4d ago), licensed MIT. It adds 279 tokens to every session and 2,165 once invoked, about $0.0014 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 agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

model-compatibility

Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.

Yeachan-Heo/oh-my-claudecode · 0 tokens

ui-spec-designer

Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.

shinpr/claude-code-workflows · 40 tokens

check

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

mindfold-ai/Trellis · 34 tokens

design-rules

Condensed 10 Golden Rules from the Agent Design Bible.

jmagly/aiwg · 0 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens