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/sakhilchawla/skillkit/improvenpx skills add sakhilchawla/skillkit --skill improvegit clone --depth 1 https://github.com/sakhilchawla/skillkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sakhilchawla/skillkit/improve)<a href="https://agentmods.dev/skills/sakhilchawla/skillkit/improve"><img src="https://agentmods.dev/badge/skills/sakhilchawla/skillkit/improve.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00018 | $0.00515 |
| Opus 5 | $0.00009 | $0.00258 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
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 3d 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.
What it actually says
Improve
Audit the current project's AI agent configuration for quality issues.
Scope: $ARGUMENTS (default: all)
Audit 1: Skill Quality (scope: skills or all)
For each SKILL.md found in the project:
- Spec compliance — Has name, description, valid frontmatter fields?
- Staleness — When was it last modified? (
git log -1 --format=%cr -- <file>) - Redundancy — Are any skills doing substantially the same thing?
- Security — Does it request Bash without safety constraints?
- Token budget — Is the body unreasonably large?
Audit 2: Context Quality (scope: context or all)
Check CLAUDE.md, .cursorrules, and similar context files:
- Accuracy — Do referenced files/paths still exist?
- Freshness — Does git history show significant changes since context was written?
- Completeness — Are there major directories or patterns not mentioned?
Audit 3: Gap Analysis (scope: all)
Check for common workflows that could benefit from skills:
- Does the project have a shipping/PR workflow skill?
- Does it have a testing discipline skill?
- Does it have a review/quality skill?
- Does it have scaffold skills for common creation tasks?
Output Format
## Skill Audit
| Skill | Status | Issues |
|-------|--------|--------|
| review | ✓ Good | None |
| ship | ⚠ Stale | Not modified in 90+ days |
## Context Audit
| File | Status | Issues |
|------|--------|--------|
| CLAUDE.md | ⚠ Outdated | References deleted directory |
## Recommendations
1. [Priority] <specific action with expected impact>
2. ...
## Gaps
- Missing: /scaffold skill — would save ~15min per new component
Rules
- Report findings, do NOT auto-apply changes
- Each recommendation must include: what to change, why, expected impact
- Prioritize by impact: security > correctness > freshness > completeness
- Do not recommend adding skills the project doesn't need
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.
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.
- 3d ago First seen · 67 lines · 18 tokens per session scan A 32bec4368c54
improve is a skill published in the GitHub repository sakhilchawla/skillkit (6 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 515 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…