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/kenn-io/msgvault/claude-codenpx skills add kenn-io/msgvault --skill claude-codegit clone --depth 1 https://github.com/kenn-io/msgvaultWhat 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 | $0.00084 | $0.01261 |
| Opus 5 | $0.00042 | $0.00630 |
| Sonnet 5 | $0.00017 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
msgvault-query 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
msgvault-query
Run SQL against the msgvault archive via msgvault query. The analytics cache is DuckDB over Parquet — queries run in milliseconds. No DuckDB binary or Parquet path knowledge required.
The analytics cache is built automatically when stale or missing.
Quick Start
# Top 10 senders, table format
msgvault query --format table "SELECT from_email, message_count FROM v_senders ORDER BY message_count DESC LIMIT 10"
# Messages from a domain in 2024, CSV output
msgvault query --format csv "SELECT subject, sent_at, from_email FROM v_messages WHERE from_domain = 'example.com' AND year = 2024 ORDER BY sent_at DESC"
# Label distribution as JSON
msgvault query "SELECT name, message_count, total_size FROM v_labels ORDER BY message_count DESC"
Available Views
See references/views.md for full column schemas.
Base views (direct Parquet data)
| View | Description |
|---|---|
messages |
Raw message metadata partitioned by year |
participants |
Email addresses with domain and display name |
message_recipients |
Message-to-participant links (from/to/cc/bcc) |
labels |
Gmail label names |
message_labels |
Message-to-label links |
attachments |
Attachment metadata (filename, size) per message |
conversations |
Thread grouping |
sources |
Synced accounts |
Convenience views (pre-joined aggregates)
| View | Description |
|---|---|
v_messages |
Messages with resolved sender (from_email, from_name, from_domain) and labels as JSON array |
v_senders |
Per-sender aggregates: message_count, total_size, attachment stats, first/last message |
v_domains |
Per-domain aggregates: message_count, total_size, sender_count |
v_labels |
Per-label aggregates: message_count, total_size |
v_threads |
Per-conversation aggregates: message_count, date range, participant_emails as JSON array |
Output Formats
msgvault query "..." # JSON (default): {"columns":[...], "rows":[...], "row_count":N}
msgvault query --format csv "..." # CSV with header row
msgvault query --format table "..." # Aligned text table with row count
What ships with it
1 file 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 · 157 lines · 84 tokens per session scan A 776782d62f28
msgvault-query is a skill published in the GitHub repository kenn-io/msgvault (2,047 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,261 once invoked, about $0.0004 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 2026-08-30.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.