codebase-improvement-planner

A process for inspecting an existing codebase and creating a ranked improvement backlog when no specific change has been chosen. It considers maintainability, reliability, tests, architecture, tools, dependencies, and operations.

In plain words
What is it for?
Use it when you want to know what to improve next in an existing repository. It can recommend a bounded maintenance task after the improvement priority is approved.
Why use it?
It turns a vague request to improve a project into evidence-based priorities. It identifies the highest-value next upgrade instead of treating every possible improvement as equally important.

Skill for Claude CodeCodex

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 skills/cmdr-chara/codex-toolkit/codebase-improvement-planner
Any agent
npx skills add cmdr-chara/codex-toolkit --skill codebase-improvement-planner
Clone the repo
git clone --depth 1 https://github.com/cmdr-chara/codex-toolkit

Made for: Claude Code, Codex.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,906 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 $0.00112 $0.02906
Opus 5 $0.00056 $0.01453
Sonnet 5 $0.00022 $0.00581
Haiku 4.5 $0.00011 $0.00291

Measured 2d ago against content hash 559408bd8bfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-improvement-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 2d 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.

skills/codebase-improvement-planner/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Improvement Planner

Turn an open-ended “make this codebase better” request into a ranked, evidence-backed improvement backlog and one defensible next upgrade.

Trigger boundary

Use this skill for:

  • “Inspect this repository and tell me what we should improve next.”
  • “Audit the codebase and separate major, medium, and minor improvements.”
  • “What is the highest-value technical upgrade we can make without a predefined task?”
  • “Find maintainability, reliability, testing, architecture, tooling, dependency-health, and operational improvements, then recommend the next move.”
  • “Improve this codebase” when the user has not already specified the exact change.

Do not trigger for:

  • a known framework, runtime, dependency, API, schema, storage, or compatibility transition—use codebase-evolution-controller;
  • a concrete failure or regression whose cause is unknown—use debugging-investigator;
  • a named slow path with a measurable performance objective—use optimize-codebase-performance;
  • review or refactoring of an already-defined diff or code area—use review-and-refactor-code;
  • broad architecture or ownership mapping where no improvement decision is requested—use repository-intelligence;
  • platform-specific production implementation or audit—use the applicable web or mobile builder;
  • integrated release readiness—use verification-and-release.

This skill owns opportunity discovery, classification, prioritization, and next-upgrade selection. It does not absorb specialist workflows after the winning improvement is known.

Required inputs

Obtain or state:

  1. repository root and current working-tree state;
  2. the user’s goal, if any, such as reliability, maintainability, delivery speed, cost, quality, or modernization;
  3. important product or operational constraints;
  4. excluded paths, generated/vendor boundaries, and protected contracts;
  5. available build, test, lint, type-check, benchmark, CI, and deployment evidence;
  6. whether the request is discovery only or also authorizes implementation after a proposal.

Read the full file on GitHub · 278 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 278 lines · 112 tokens per session scan A 559408bd8bfd

Subscribe to this mod's changes

codebase-improvement-planner is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 2,906 once invoked, about $0.0006 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 skills, from other repositories