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.
npx agentmods add skills/drn/dots/improvenpx skills add drn/dots --skill improvegit clone --depth 1 https://github.com/drn/dotsWhat 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.
| Model | Per session | Once 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 |
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 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.
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.
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.
- 2d ago First seen · 482 lines · 25 tokens per session scan A f14d7b36ae46
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…