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/flukeatzerocool/infobroker/summarizationnpx skills add flukeatzerocool/infobroker --skill summarizationgit clone --depth 1 https://github.com/flukeatzerocool/infobrokerWrote 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/flukeatzerocool/infobroker/summarization)<a href="https://agentmods.dev/skills/flukeatzerocool/infobroker/summarization"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/summarization.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 | $0.00050 | $0.00580 |
| Opus 5 | $0.00025 | $0.00290 |
| Sonnet 5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
summarization 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarization
When NOT to Use
- When the source is already very short (under 100 words); offer to highlight key sentences instead.
- When the user needs exact quotes rather than a paraphrase.
Workflow
-
Analyze the input. Determine length, structure, domain, and whether it is one document or many.
-
Choose the strategy.
- Extractive: Keep key sentences verbatim for factual or legal texts.
- Abstractive: Rewrite in new words for readability.
- Hierarchical: Provide a one-line TLDR, a short paragraph, and a detailed breakdown.
- Multi-document: Synthesize across several sources.
-
Identify key information. Extract core claims, findings, decisions, action items, and supporting data. Rank by importance.
-
Generate the summary. Match the requested length and detail. Preserve factual accuracy. Do not introduce information not in the source.
-
Verify faithfulness. Compare the summary against the source. Check numbers, proper nouns, and causal claims.
Best Practices
- Front-load the most important information.
- Preserve numerical precision.
- Match the source's tone.
- For multi-document summaries, organize by theme rather than by source.
- Flag contradictions rather than choosing one side.
Output Contract
Always end with a searchable one-line status:
summarization complete. <N> key points | source facts preserved: <pass/flag>
<pass/flag> is pass when the summary preserves the source's numbers,
proper nouns, and causal claims, otherwise flag with the discrepancy
noted.
Edge Cases
- Contradictory source: Highlight the contradiction in the summary.
- Technical jargon: Define terms for non-specialists; preserve vocabulary for experts.
- Truncated source: Note that the summary may be incomplete.
- Overlapping sources: Deduplicate repeated information.
Infobroker Integration
This skill is the condense step of the Infobroker Research & Write and
Fact-Check pipelines. It condenses verified findings into a concise digest
before technical-writing produces the final output.
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 · 77 lines · 50 tokens per session scan A c1a36560843e
summarization is a skill published in the GitHub repository flukeatzerocool/infobroker (0 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 580 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…