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-resumenpx skills add franzos/claude-plugins --skill plan-resumegit 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 | $0.00055 | $0.00684 |
| Opus 5 | $0.00028 | $0.00342 |
| Sonnet 5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
plan:resume 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resuming 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.
1. Find the checkpoint
Look in $KB/<project>/checkpoints/, where <project> is the repo's folder name.
Take the newest file by date in the filename. If several slugs are in play, list them with their dates and ask the user which. If there is no checkpoints directory, this is not a resume - use /plan:run.
Read the checkpoint first. Its header names the plan and spec - read those next, then the rest of its "Read first" list, in the order it names them. Honour its staleness warnings: if it says a file is not to be trusted, do not read it for facts.
If the header is missing (a checkpoint written before this was required, or by hand), find the plan yourself: strip the date from the checkpoint filename and match the remaining slug against $KB/<project>/plans/. The dates will not match - the plan is dated when it was written, the checkpoint when work stopped.
2. Verify before trusting it
The checkpoint describes the tree as it was when work stopped. Confirm it still holds before acting on it. Things move: the user may have committed, merged, reverted, or reboot may have lost something.
Check, at minimum:
git log --onelineandgit statusagainst the commits and branch the checkpoint claims.- The test suite against the pass/fail count it claims.
- Whether the containers, databases, or services it describes are actually in the state it describes.
This is cheap and it is the whole point of the checkpoint being trustworthy.
3. Report the delta
Tell the user, in a few lines:
- What the checkpoint claimed.
- What is actually true now.
- Whether the stated next action is still the right one.
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 · 54 lines · 55 tokens per session scan A c794118afc51
plan:resume is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 21d ago), licensed MIT. It adds 55 tokens to every session and 684 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…