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/dcosson/h2/plan-summarizenpx skills add dcosson/h2 --skill plan-summarizegit clone --depth 1 https://github.com/dcosson/h2What 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 | $0.00046 | $0.02078 |
| Opus 5 | $0.00023 | $0.01039 |
| Sonnet 5 | $0.00009 | $0.00416 |
| Haiku 4.5 | $0.00005 | $0.00208 |
Grade A, and why
plan-summarize 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 3d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Summarize
Generate a planning summary doc with aggregate statistics across plan docs AND their companion test harness docs. Supports multiple review rounds — each round is summarized in its own section. Tracks convergence across rounds via two key metrics: total suggested changes per round and total incorporated changes per round.
Inputs
$0: Output file path (e.g.,docs/plans/00-planning-review-summary.md)$1(optional): Glob pattern for plan docs (default:docs/plans/0*.md, excluding index/architecture/shaping/summary docs)
Phase 0: Run Automated Aggregation
Before reading any files manually, run the aggregation script to get accurate numbers:
python3 "$(dirname "$0")/aggregate-dispositions.py" docs/plans/ --format json > /tmp/disposition-aggregate.json
python3 "$(dirname "$0")/aggregate-dispositions.py" docs/plans/ --format markdown
The JSON output provides machine-precise numbers. The markdown output gives you a human-readable overview. Use these numbers as the source of truth for all convergence numbers, severity breakdowns, per-file findings, and incorporation rates. Do NOT manually count findings by reading files — that is error-prone and slow.
The script handles all known disposition table format variants (numbered section headers, Round N labels, severity normalization from Critical/Blocker to P0, etc.) and produces consistent normalized output.
Phase 1: Discover Documents
- Find all plan docs matching the pattern (exclude
00-*,99-*,*-test-harness*,SKILL-*) - Find all companion test harness docs
- Build a list of all doc pairs (plan + TH)
Important: Both plan docs AND test harness docs contain disposition tables. You MUST parse disposition tables from BOTH types of documents. Test harness docs often have their own review findings (testing gaps, missing scenarios, stale assertions) that are tracked separately from the plan doc findings.
Phase 2: Parse Disposition Tables
For each doc (plan and TH), find ALL disposition table sections. Docs may have:
## Review Disposition(single round, treat as Round 1)## Round 1 Review Disposition,## Round 2 Review Disposition, etc. (multi-round)
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.
- 3d ago First seen · 141 lines · 46 tokens per session scan A 85b3124f2a08
plan-summarize is a skill published in the GitHub repository dcosson/h2 (159 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 2,078 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 2026-08-30.
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.
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…