improve

A project-improvement workflow that examines a codebase and updates its AI-assistant instructions, rules, settings, or agents.

In plain words
What is it for?
Use it for a full improvement pass or to update only AGENTS.md, rules, settings, or agent configuration. A scan mode reports recommendations without changing files.
Why use it?
It helps keep the assistant's project guidance aligned with the actual technology, file structure, and working practices.

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/bostonorange/claude-code-framework/improve
Any agent
npx skills add BostonOrange/claude-code-framework --skill improve
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,358 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00026 $0.01358
Opus 5 $0.00013 $0.00679
Sonnet 5 $0.00005 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured yesterday against content hash d80119c40f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

improve scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

| No .codex/ directory | Run setup.sh first (print instructions) |
.agents/skills/improve/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve — Framework Self-Improvement

Analyze the current project state and improve the .codex/ configuration for better AI assistance.

Usage

/improve                  — Full improvement pass (all areas)
/improve agents-md        — Update AGENTS.md only (fill placeholders, add patterns)
/improve rules            — Update rule file patterns to match actual project
/improve settings         — Update permissions and model config
/improve agents           — Tune agent tools and models for project needs
/improve scan             — Report only, no changes (dry run)

Process

Phase 1: Project Discovery

Scan the project to build a comprehensive profile:

  1. Tech stack detection:
# Package managers and dependency files
ls package.json requirements.txt Pipfile go.mod Cargo.toml build.gradle pom.xml Gemfile composer.json sfdx-project.json 2>/dev/null
  1. File type census:
find . -type f -not -path "*/.git/*" -not -path "*/node_modules/*" -not -path "*/__pycache__/*" -not -path "*/vendor/*" -not -path "*/.next/*" -not -path "*/dist/*" -not -path "*/build/*" | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -20
  1. Framework detection: Read config files (next.config., vite.config., angular.json, etc.)

  2. Directory structure: Map the top-level architecture

  3. Existing tooling: Find linter configs, test configs, CI configs

Phase 2: AGENTS.md Improvement

Read current AGENTS.md and check:

  1. Unfilled placeholders: Find any remaining {{...}} and fill from discovered data:
    • {{PROJECT_DESCRIPTION}} — from README.md, package.json description, etc.
    • {{TECH_STACK_TABLE}} — build from dependency files
    • {{CODE_STRUCTURE}} — generate directory tree
    • {{CODING_STANDARDS}} — infer from linter configs (.eslintrc, .prettierrc, pyproject.toml, etc.)
    • {{ERROR_HANDLING_PATTERN}} — find common error patterns in code
    • {{TESTING_STRATEGY}} — infer from test config and existing tests
    • {{INTEGRATIONS}} — list discovered external services

Read the full file on GitHub · 158 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 · 158 lines · 26 tokens per session scan B d80119c40f77

Subscribe to this mod's changes

improve is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,358 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens