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/shippy/personal-intelligence-kit/cross-source-queriesnpx skills add shippy/personal-intelligence-kit --skill cross-source-queriesgit clone --depth 1 https://github.com/shippy/personal-intelligence-kitWhat 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 | $0.00051 | $0.00983 |
| Opus 5 | $0.00026 | $0.00491 |
| Sonnet 5 | $0.00010 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
cross-source-queries 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Source Queries
Analysis tools that detect patterns across multiple data sources. Each analysis reads vault.toml to discover which sources are enabled and skips missing ones gracefully.
The intention-reality analysis uses an LLM (Claude Sonnet or GPT) for semantic goal assessment against weekly reflections when ANTHROPIC_API_KEY (or OPENAI_API_KEY) is set, and falls back to regex heuristics otherwise. The other two analyses use regex-based heuristics and have EXTENSION POINT comments marking where to add LLM calls.
Invocation
cd .claude/skills/cross-source-queries
uv run generate_report.py # Run all three analyses
uv run intention_reality_gaps.py # Just intention-reality
uv run commitment_accountability.py # Just commitments
uv run serendipity_convergence.py # Just convergence
Or via Claude Code: batch: cross-source-queries
Available Analyses
1. Intention ↔ Reality Gaps (intention_reality_gaps.py)
Compare stated yearly goals vs actual behavior, primarily via weekly reflections.
What it does:
- Finds goal files in notes vault (e.g., "2026 Goals.md") and parses them structurally (sections, sub-goals, checkbox/strikethrough state)
- LLM path (when
ANTHROPIC_API_KEYorOPENAI_API_KEYis set): feeds the goals, all weekly reflections inoutput/reflections/, and supplementary keyword-match signals into a single LLM call that classifies each goal asactive/stale/neglected/completed/postponed - Heuristic fallback (no API key): keyword-matches each goal against notes, email, and tasks — noisy but runs offline
- Appends recent intentions from
journal.db
Output: output/reports/intention-reality-YYYY-MM-DD.md
Data sources: notes vault, output/reflections/, journal.db, tasks.db, email (notmuch)
2. Commitment Accountability (commitment_accountability.py)
Track commitments made in email and check follow-through.
What it does:
- Scans sent emails for commitment phrases (regex patterns)
- Checks for follow-up emails to same recipient
- Flags commitments without follow-through
What ships with it
4 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 · 89 lines · 51 tokens per session scan A 6e94d0f76147
cross-source-queries is a skill published in the GitHub repository shippy/personal-intelligence-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 983 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…