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 mshadmanrahman/claude-for-designers --skill stuckgit clone --depth 1 https://github.com/mshadmanrahman/claude-for-designersWrote 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/mshadmanrahman/claude-for-designers/stuck)<a href="https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/stuck"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/stuck/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/mshadmanrahman/claude-for-designers/stuck"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/stuck.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 | $0.00161 | $0.03438 |
| Opus 5 | $0.00081 | $0.01719 |
| Sonnet 5 | $0.00032 | $0.00688 |
| Haiku 4.5 | $0.00016 | $0.00344 |
Grade A, and why
stuck 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 12d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The student typed /stuck and nothing else. That is the whole input, and it is deliberate.
Do not ask them what is wrong. Do not ask them to describe the problem, paste an error, or say which step they are on. Most of this room reads and writes English as a second language, and having to explain a broken setup in English is the thing that stops people asking for help at all. So you look at the folder, work it out, and tell them what you found.
Create no file. This skill writes nothing to disk unless the fix itself is a file change and the student says yes to it first.
The one rule
Name one blocker and one fix. Then stop.
A student running this is already lost. A list of eight possibilities asks them to triage, and triage is the thing they cannot do right now. So walk the chain below in order, stop at the first check that fires, and say only that.
Once they tell you it is fixed, run the chain again from the top and give them the next one.
Step 1. Read before you speak
Look at all of this before you write a single sentence:
- Which folder you are open in. Does it hold
CLAUDE.md,principles/,projects/,skills/andcareer-vault/? Or does it holdcontext.mdandclaude-contract.md, which means you are inside one project folder. - Whether
.claude/skills/exists at the course-folder root, and how many command folders sit inside it. - Which folder inside
projects/is theirs. A folder that is notedubridgeand not_new-clientis theirs. If there is none, EduBridge is their project, which is a normal choice. - Every headline file in the class table in
CLAUDE.md, and for each one whether it is still course scaffolding or the student's own writing. - Whether any
*.example.mdfile has been edited, and whether a student file matches the.example.mdbeside it closely enough to be a copy.
A file is still scaffolding if any of these is true:
- A
YOUR TURNheading is there with the prompts still sitting in HTML comments under it. - It still holds
COURSE SCAFFOLDING,COURSE NOTE for the student,DELETE EVERYTHING ABOVE, orDELETE EVERYTHING EXCEPT. - The only filled part is the labelled EXAMPLE section, which is the instructor's.
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.
- 12d ago First seen · 215 lines · 161 tokens per session scan A 05cc87f5f411
stuck is a skill published in the GitHub repository mshadmanrahman/claude-for-designers (28 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 3,438 once invoked, about $0.0008 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
career-path-planner
Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
course-material-creator
Create custom educational materials including syllabi, lesson plans, assessments, reading lists, and learning objectives. Use when building course curricula, training programs, workshops, or educational content.
debate-practice-coach
Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics. Use when preparing for debates, improving persuasion skills, or practicing argumentation.
explain
Explain something in depth on request. Use when the user writes "???" - alone, or placed directly after a reference, statement, or term - which means "explain that in more detail, with a concrete example AND consequences". Also invoked by the /credo:explain command. Treat the pointed-at subject as the thing to…
survey-design
Design publication-quality academic questionnaires with self-evaluation scoring. Use this skill when users want to design a survey, questionnaire, or measurement scale for academic research or journal submission. Also trigger when users mention scale development, questionnaire validation, Likert scale design…