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-runnpx skills add franzos/claude-plugins --skill plan-rungit 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 | $0.00070 | $0.01641 |
| Opus 5 | $0.00035 | $0.00821 |
| Sonnet 5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
plan:run 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executing a 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.
Run this in a fresh session. Execution in the same session that wrote the plan starts at 100k+ of context and pays that on every turn for the rest of the run.
Run it autonomously
Work the whole plan through without checking in. The user already signed the plan off. Do not ask permission to start a task, to move to the next one, or to act on the commit answer they give you in section 1.
Report at milestones, not per task - a short line when a group of related tasks lands, not a narration of each one.
There are exactly four reasons to stop and ask:
- The two run questions at the start (section 1), asked together, once.
- A task contradicts the spec, or doing it would change scope (section 3).
- Something is genuinely ambiguous and both readings lead to materially different work.
- The context thresholds below.
Anything else - a task that needs a small mechanical deviation, a pre-existing failure, a judgment call with an obvious default - decide it, note it, keep going.
1. Load
Find the plan under $KB/<project>/plans/. If several match, take the newest by date and say which one you took.
Check $KB/<project>/checkpoints/ first. If a checkpoint exists for this slug, this is a resume, not a fresh run - use /plan:resume instead.
Read, in this order: the spec, the plan, then the project's CLAUDE.md (repo root first, then $KB/<project>/CLAUDE.md). Read the files the plan names as you reach the tasks that touch them, not up front.
Record the starting state before touching anything: current branch, whether the tree is clean, and the current pass/fail count. This is the baseline you will compare against at the end.
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 · 119 lines · 70 tokens per session scan A f139025258a0
plan:run is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 20d ago), licensed MIT. It adds 70 tokens to every session and 1,641 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…