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 skills add petekp/claude-code-setup --skill frame-checkgit clone --depth 1 https://github.com/petekp/claude-code-setupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/petekp/claude-code-setup/frame-check)<a href="https://agentmods.dev/skills/petekp/claude-code-setup/frame-check"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/frame-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/petekp/claude-code-setup/frame-check"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/frame-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00000 | $0.01917 |
| Opus 5.5 | $0.00000 | $0.00767 |
| Sonnet 5.5 | $0.00000 | $0.00383 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
frame-check 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 1mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frame check
Most failed work is not a wrong answer. It is a right answer to the wrong question. Kimball named this the error of the third kind in 1957 and Mitroff built a practice on it. The work is rigorous, the execution is clean, and it is aimed at something that was never the problem.
Catch it before the work commits.
What you are looking for
A problem statement arrives sounding like an observation. "Onboarding is too slow." "Users are confused." "It's a race condition." None of those are observations. Someone watched something, selected part of it, decided what it meant, and concluded — and the sentence you received is the last link with the chain removed. Your job is to put the chain back and ask what else the bottom of it supports.
Two different failures produce a wrong problem, and they need different tools.
The conclusion outran the evidence. What was observed supports several readings, and one got picked without anyone noticing a choice was made. Argyris's ladder of inference is the tool here: walk back down to what a camera would have recorded.
The evidence is sound and the goal is wrong. The diagnosis holds up and is aimed at an objective nobody has examined. Climbing down the ladder will never find this, because the goal never entered as evidence. Argyris's double-loop learning is the tool: ask which governing goal makes this count as a problem at all.
Check the first. Check the second before you finish.
1. Get rung one before you say anything
The bottom rung is observable data — what a recording device would have captured, before anyone interpreted it. Go find it. An assertion about the evidence that you did not actually check is the same error you are here to catch.
Where rung one usually hides:
- A recurring bug.
git logthe file. Has this been "fixed" before, and what did each fix assume? Three fixes to one symptom is strong evidence the frame is wrong, not that the engineers were careless. - An incident or failure. The raw stack trace and log lines, not the summary of them. Summaries are already rung three.
- A metric. How the dashboard actually computes it, in the query or the event definition. Metric names drift from metric definitions constantly, and a problem stated in terms of a name is often a problem about something else.
- A user complaint. The verbatim, not the paraphrase in the ticket title.
- A "slow" or "flaky" claim. The actual numbers and their distribution. "Slow" is never rung one.
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.
- 1mo ago First seen · 172 lines · 0 tokens per session scan A a66fad9f4682
frame-check is a skill published in the GitHub repository petekp/claude-code-setup (48 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,917 tokens. 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 2026-09-04.
Other skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
workspaces
How an Open SWE workspace's sandbox image works and how to change it — create one, edit or fork an existing one, start from scratch, what setupscript and updatescript are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in progress. Read this whenever someone asks about…
linear-tickets
Create or update high-quality Linear tickets while preserving the originating report, diagnostic links, attachments, and reporter/requester attribution. Read this whenever someone asks to create, recreate, or update a Linear issue.
generative-ui
Use when presenting information already in hand as a small, static structured panel in the conversation — status, results, comparisons, or a compact summary — rather than prose, a markdown table, a widget, or an app.
st-widget-builder
Use when the user asks to render, build, visualise, mock up, or show a widget (chart, dashboard, card, table, graph) in the Mewbo Console. Teaches how to delegate the work to the st-widget-builder sub-agent instead of writing HTML or inline code yourself.