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/yellowbee686/everything-analysis-agent/qmd-analysisnpx skills add yellowbee686/everything-analysis-agent --skill qmd-analysisgit clone --depth 1 https://github.com/yellowbee686/everything-analysis-agentWrote 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/yellowbee686/everything-analysis-agent/qmd-analysis)<a href="https://agentmods.dev/skills/yellowbee686/everything-analysis-agent/qmd-analysis"><img src="https://agentmods.dev/badge/skills/yellowbee686/everything-analysis-agent/qmd-analysis.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 | $0.00038 | $0.00515 |
| Opus 5 | $0.00019 | $0.00258 |
| Sonnet 5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
qmd-analysis 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.
What it actually says
QMD Analysis
Use this skill for searches over the local analysis-md QMD index.
Requires qmd CLI and the local analysis-md index at ~/.cache/qmd/analysis-md.sqlite.
Core Rules
- Always call qmd with
--index analysis-md. - The default qmd index
indexis not the analysis corpus and may be empty. - Prefer BM25 for fast article listing:
qmd --index analysis-md search '全称量化' --json -n 20
- Use hybrid
queryonly when semantic recall is needed; it may trigger model downloads or reranking delays. - If using
query, consider--no-rerankwhen speed matters. - Treat qmd's
Updated: ... agoas source-document freshness, not sqlite creation time.
Local Corpus
- Collection:
analysis_md_files - Root:
/Users/bytedance/code/analysis-agent/data/analysis_md_files - Config:
~/.config/qmd/analysis-md.yml - Index:
~/.cache/qmd/analysis-md.sqlite
Clickable Links
Do not mechanically convert qmd://analysis_md_files/... to a local path. The qmd stored path can be normalized and may not match the current filename on disk.
When the user asks for clickable local links, use:
python3 skills/qmd-analysis/scripts/search_links.py '全称量化' -n 20
The script searches analysis-md, resolves qmd paths to real files under the corpus root, and emits Markdown links with absolute local paths.
Relationship To The QMD Skill
This skill is a thin project-specific wrapper around the generic qmd skill. Use the generic qmd skill for command syntax and general QMD behavior. Use this skill whenever the task involves the analysis-md index, the analysis_md_files collection, or clickable links into the local analysis corpus.
Do not duplicate the full qmd manual here.
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.
- 4d ago First seen · 55 lines · 38 tokens per session scan A c12632266ceb
qmd-analysis is a skill published in the GitHub repository yellowbee686/everything-analysis-agent (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 515 once invoked, about $0.0002 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…