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/franzos/claude-plugins/plan-snapshotnpx skills add franzos/claude-plugins --skill plan-snapshotgit clone --depth 1 https://github.com/franzos/claude-pluginsWhat 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 | $0.00065 | $0.00956 |
| Opus 5 | $0.00032 | $0.00478 |
| Sonnet 5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
plan:snapshot 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpointing an interrupted plan
$KBis your knowledge-base root: a directory outside the working repo holding<project>/specs/,<project>/plans/and<project>/checkpoints/. Point at it from your CLAUDE.md. Keeping these out of the repo keeps process artifacts from leaking into it, and the knowledge survives clones, branches and machines.
Writes $KB/<project>/checkpoints/YYYY-MM-DD-<slug>.md, dated the day work stopped. Same slug as the plan. Several checkpoints may accumulate for one plan; the newest is the live record.
The reader is a fresh session with no memory of this one. Everything it needs must be in the file or named by path in it.
The one rule
Every fact in this file is measured, now, against the tree it describes. Nothing is copied from an agent's report, and nothing is recalled from earlier in this session.
Before writing a single number, run the commands: git log --oneline, git status, the test suite, the linter. A stale checkpoint is worse than none, because the next session trusts it.
If you cannot verify something, write that you could not verify it.
Structure
Header
Two lines, before anything else. A checkpoint that cannot name its own plan is orphaned.
Plan: /absolute/path/to/kb/<project>/plans/YYYY-MM-DD-<slug>.md
Spec: /absolute/path/to/kb/<project>/specs/YYYY-MM-DD-<slug>.md
Absolute paths, verified to exist. The plan and spec carry the date they were written, which is not this checkpoint's date - only the slug matches. If there is no spec, say Spec: none.
START HERE
Open with the three things a fresh session needs in its first ten seconds:
- Is anything broken? Failing tests, a dirty tree, a half-applied migration - state it plainly, or state that nothing is broken.
- Is anything waiting? Unmerged branches, an unanswered question for the user, a service left running or stopped.
- What is the single next action? One task, named, with whether anything blocks it.
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.
- yesterday First seen · 86 lines · 65 tokens per session scan A aa852701f519
plan:snapshot is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 21d ago), licensed MIT. It adds 65 tokens to every session and 956 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.
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.