improve

A tool for improving reusable instructions for coding agents and recording useful knowledge from a work session.

In plain words
What is it for?
Use it after a session to update skills, note missing documentation or tests, record team knowledge, and prepare handoff instructions.
Why use it?
It helps preserve fixes, lessons, and project context so future sessions do not repeat the same mistakes or workarounds.

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/drn/dots/improve
Any agent
npx skills add drn/dots --skill improve
Clone the repo
git clone --depth 1 https://github.com/drn/dots

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00025 $0.06457
Opus 5 $0.00013 $0.03229
Sonnet 5 $0.00005 $0.01291
Haiku 4.5 $0.00003 $0.00646

Measured 2d ago against content hash f14d7b36ae46, 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 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Manual workarounds bypassing existing abstractions** — raw shell commands, curl calls, or inline scripts that hit APIs or services the project already has clients/CLI for, but lacked the specific operation needed. Sc
agents/skills/improve/SKILL.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve Skills, Capture Context & Knowledge

Analyze the current conversation to improve skills, fix codebase gaps, capture durable knowledge, and generate handoff prompts for skills managed outside this repository.

When to Use

Run /improve at the end of any session where:

  • Skills were invoked and required manual fixes or workarounds
  • You discovered better patterns or approaches mid-conversation
  • A skill produced output that needed multiple iterations to get right
  • Technical assumptions in a skill turned out to be wrong
  • You learned something that would make a skill work better next time
  • You hit a codebase gap (missing docs, tests, error handling, or config)
  • You learned new organizational context (people, roles, vendor contacts, processes)

Context

  • Current repo: !git rev-parse --show-toplevel 2>/dev/null | head -1
  • Skills directory: !find agents/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30
  • Context directory exists: !ls context/knowledge/index.md 2>/dev/null | head -1
  • Knowledge base index: !cat context/knowledge/index.md 2>/dev/null | head -30
  • Context directory structure: !find context -type f 2>/dev/null | head -20
  • Voice profile: !find . -maxdepth 3 -name 'voice-profile.md' -o -name 'VOICE.md' -o -name 'voice.md' 2>/dev/null | head -5
  • Argus KB available: !command -v argus 2>/dev/null | head -1
  • Argus KB index: !argus kb list 2>/dev/null | head -200
  • Argus KB recent changes: !tail -30 ~/.dots/sys/kb-changes/changes.jsonl 2>/dev/null | head -30

Instructions

When /improve is invoked:

Step 0a: Load Argus KB Context (if available)

If the dynamic context above shows argus is on PATH and the KB index is non-empty, the Argus KB is the primary durable store. Load it before doing anything else.

See references/argus-kb.md for the full load procedure (which docs to read, MCP tool name fallbacks, search heuristics). Summary: always-load memory/user/ + memory/feedback/ (or rely on the SessionStart hook), then kb_search on session-relevant keywords and read top matches.

Read the full file on GitHub · 482 lines

Files

What ships with it

1 file 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 · 482 lines · 25 tokens per session scan A f14d7b36ae46

Subscribe to this mod's changes

improve is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 6,457 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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