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/analysis-loopnpx skills add flukeatzerocool/infobroker --skill analysis-loopgit clone --depth 1 https://github.com/flukeatzerocool/infobrokerWhat 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 | $0.00169 | $0.03096 |
| Opus 5 | $0.00084 | $0.01548 |
| Sonnet 5 | $0.00034 | $0.00619 |
| Haiku 4.5 | $0.00017 | $0.00310 |
Grade A, and why
analysis-loop 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 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.
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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Loop
Disciplined research workflow: scope the question → collect and assess sources → analyze and synthesize → disseminate and refine. One question completes its full cycle before the next starts.
When NOT to Use
- Single-source factual lookup — use
web_searchdirectly. - The user wants the AI's internal knowledge, not web research.
- The
infobrokerskill is already loaded and routed the request to a lighter workflow shape — those handle lighter research. This skill is for when rigor matters.
Phase 0 — Question Scoping
The most important phase. A poorly scoped question produces garbage output regardless of collection quality. Modeled on the Planning & Direction step of the intelligence cycle.
If the user's question is vague
Ask targeted clarifying questions. Use these dimensions:
-
Intelligence requirement. What decision does this research serve? "I want to know about AI safety" is not scoped. "I need to decide whether to adopt an AI safety policy for our LLM deployment, and I need to know what current regulatory frameworks require" is.
-
Essential Elements of Information (EEIs). Decompose into specific, answerable sub-questions. Example for "Is Rust ready for kernel development?":
- Which major kernels/OS projects have merged Rust code?
- What are the current limitations of Rust in kernel contexts?
- What toolchain support exists for cross-compilation to kernel targets?
- What is the community and maintainer stance?
-
Scope boundaries. State what is explicitly out of scope. Example: "Linux kernel only — not Windows, BSD, or embedded RTOS."
-
Priority tiering. Classify sub-questions:
- Must answer — core; research is incomplete without this.
- Should answer — important context.
- Could answer — nice-to-have.
-
Audience and format. Who consumes this? CISO needs executive summary and risk ratings. Engineer needs technical depth. Researcher needs full methodology and citation trail.
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.
- 2d ago First seen · 349 lines · 169 tokens per session scan A c58f7362aa5e
analysis-loop is a skill published in the GitHub repository flukeatzerocool/infobroker (0 stars, last pushed 7d ago), licensed MIT. It adds 169 tokens to every session and 3,096 once invoked, about $0.0008 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…