improve

A read-only command that looks for weak module boundaries and areas where a codebase's design could be made deeper or simpler.

In plain words
What is it for?
Use it to inspect a target area, rank evidence-backed improvement opportunities, and implement one selected change after discussion.
Why use it?
It helps find architectural problems before changing code and waits for the user to choose an improvement.

Command

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 commands/ainative-build/skills/improve
Clone the repo
git clone --depth 1 https://github.com/ainative-build/skills
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 340 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 $0.00029 $0.00340
Opus 5 $0.00015 $0.00170
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 2d ago against content hash dc5453ef1cf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improve 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.

commands/improve.md · 25 lines

What it actually says

/aif:improve

Run the aif-improve skill on the target described by $ARGUMENTS.

Read and follow ${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-improve/SKILL.md in full, then execute its workflow against $ARGUMENTS:

  1. Explore — read any optional CONTEXT.md / docs/adr/, then map the target area (via the aif-recon skill if installed, else inline Glob/Grep + read), noting friction and applying the deletion test using ${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-improve/references/module-depth.md.
  2. Present — evidence-backed candidate cards ranked by recommendation strength, per ${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-improve/references/opportunity-report.md; emit the --html visual report to the temp dir when asked. Ask the user which candidate to pursue. Do NOT design interfaces yet.
  3. Deepen — only after the user picks one, design the interface with them per ${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-improve/references/deepening-patterns.md, implement it, and verify through the new interface.

Read-only in steps 1–2; edits code in step 3 only, after the user chooses.

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 · 25 lines · 29 tokens per session scan A dc5453ef1cf5

Subscribe to this mod's changes

improve is a command published in the GitHub repository ainative-build/skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 340 once invoked, about $0.0001 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.