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/hknc/claude-evolve/summarize-efficientlynpx skills add hknc/claude-evolve --skill summarize-efficientlygit clone --depth 1 https://github.com/hknc/claude-evolveWrote 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/hknc/claude-evolve/summarize-efficiently)<a href="https://agentmods.dev/skills/hknc/claude-evolve/summarize-efficiently"><img src="https://agentmods.dev/badge/skills/hknc/claude-evolve/summarize-efficiently.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 | $0.00069 | $0.01031 |
| Opus 5 | $0.00034 | $0.00515 |
| Sonnet 5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
summarize-efficiently 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize Efficiently Skill
You compress information while preserving what matters, adapting to the user's needs.
Philosophy
- Preserve signal - Keep insights, cut filler
- Respect hierarchy - Most important first
- Match depth to need - One-liner vs detailed depends on context
- Actionable - Highlight what user should do or know
Process
1. Understand What to Summarize
| Content Type | Focus On |
|---|---|
| Document/Article | Key claims, evidence, conclusions |
| PR/Code changes | What changed, why, impact |
| Conversation | Decisions, action items, open questions |
| Meeting notes | Outcomes, owners, deadlines |
| Codebase | Architecture, patterns, entry points |
| Error logs | Root cause, frequency, affected areas |
2. Determine Compression Level
Ask if unclear, or infer from context:
| Level | Output | Use When |
|---|---|---|
| One-liner | 1 sentence | Quick check, already familiar |
| Key points | 3-5 bullets | Need to understand essentials |
| Executive | 1 paragraph | Share with stakeholders |
| Detailed | Structured sections | Deep understanding needed |
3. Extract Key Information
Read/analyze the content and identify:
- Core message - What's the main point?
- Key facts - Numbers, names, dates that matter
- Decisions/Actions - What was decided or needs doing
- Implications - What does this mean for the reader
4. Structure the Summary
One-liner:
This PR adds rate limiting to prevent API abuse using Redis token buckets.
Key points:
## Key Points
- Rate limiting added to all authenticated endpoints
- Uses Redis token bucket (100 req/min default)
- Returns 429 with Retry-After header when exceeded
- Config in env vars, no code changes needed to adjust
Executive:
## Summary
This PR implements API rate limiting to address the abuse incidents from last week.
It uses Redis-backed token buckets with configurable limits (default 100 req/min).
Users hitting limits get 429 responses with retry guidance. The implementation
adds ~2ms latency per request but prevents the cascade failures we saw.
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.
- 4d ago First seen · 169 lines · 69 tokens per session scan A d2e3263c78f0
summarize-efficiently is a skill published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 69 tokens to every session and 1,031 once invoked, about $0.0003 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…