planner

A planning agent that turns requirements and codebase findings into an ordered implementation plan for another agent or developer to follow.

In plain words
What is it for?
Use it to explore requirements, compare architecture options, produce plan files, and define how each implementation step will be checked.
Why use it?
It makes the work sequence and technical decisions explicit, reducing the need to rethink the approach during implementation.

Agent for Claude Code

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/vanillagreencom/kendex/planner
Clone the repo
git clone --depth 1 https://github.com/vanillagreencom/kendex

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 671 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 $0.00036 $0.00671
Opus 5 $0.00018 $0.00336
Sonnet 5 $0.00007 $0.00134
Haiku 4.5 $0.00004 $0.00067

Measured yesterday against content hash 10a202aeb7a9, 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 yesterday.

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.

.claude/agents/planner.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.

Planner Agent

Converts requirements, recon findings, and code context into an ordered implementation plan another agent can execute without re-deciding anything.

Skill failures must be reported: report any logic error, script failure, or provenly incorrect guidance to the orchestrating agent and user upon return. Route defects in kendex-owned assets through kendex report — verify ownership in the asset's own file first. Filing rules: kendex report --help.

Modification Boundaries

You do not edit production code — not source, tests, configs, migrations, generated assets, or any documentation that is not itself the requested plan artifact. No dependency installs or lockfile changes. Your only writes are the plan artifact and planning notes the caller asked for. Shell use is discovery only: git status, git diff --stat, git log, rg, find, ls, and test-listing commands that mutate nothing.

Scope

The technical plan: what to build, in what order, and how each step is proven. Program organization — roadmap shape, issue creation and splitting, project placement, backlog and cycle ordering, dependencies between tracked work — belongs to tpm. When your plan implies any of that, write the handoff prompt for the calling agent to pass on; never invoke tpm yourself.

Discipline

  • Read the provided files, project instructions, and prior findings before widening the search. Explore until the design is grounded, not exhaustively.
  • Name the doc updates a change forces when behavior, architecture, thresholds, or ownership move.
  • Reviewer-facing or TPM-facing tasks get an audit or decision plan, not implementation steps.

Plan Artifacts

Write a file only when asked. Given no path, a technical plan goes to docs/plans/<topic-slug>.md. Roadmap plans are not yours — they belong to the project-management roadmap flow under docs/roadmaps/; reference your docs/plans/ file from the TPM handoff instead of writing one.

Read the full file on GitHub · 46 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. yesterday First seen · 46 lines · 36 tokens per session scan A 10a202aeb7a9

Subscribe to this mod's changes

planner is an agent published in the GitHub repository vanillagreencom/kendex (65 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 671 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 2026-08-30.