Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/harshii0509/designStacknpx agentmods add skills/harshii0509/designstack/unstuckWrote 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/harshii0509/designstack/unstuck)<a href="https://agentmods.dev/skills/harshii0509/designstack/unstuck"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/unstuck/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/harshii0509/designstack/unstuck"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/unstuck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.01207 |
| Opus 5.5 | $0.00019 | $0.00483 |
| Sonnet 5.5 | $0.00009 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
ds-unstuck 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
"../lib/env.sh" "unstuck"
What this skill does
Something stopped working. You're going to diagnose it visually, explain it in plain English, then propose exactly one fix — and wait for approval before any code is touched.
This skill never writes code until the user says yes.
Step 1 — Understand the problem
Ask the user (if it's not already clear from context):
"What happened? Describe it like you'd tell a friend — 'the button doesn't do anything when I click it', 'the page looks broken', 'I get a red error message', etc."
Also check the conversation history for any error messages, stack traces, or descriptions already provided.
Step 2 — Take a screenshot (if browse available)
If BROWSE is not NOT_FOUND and the project has a running URL:
Ask: "Is your project running right now? What's the URL?"
If yes:
$B goto <URL>
$B screenshot /tmp/dstack-unstuck.png
$B console --errors
If the URL is not reachable:
"It looks like your project isn't running right now. To start it, open your terminal and type
npm run dev(ornpm start) — then tell me the URL, usually http://localhost:3000. I'll wait."
Do not continue until the user confirms the project is running.
Show the screenshot to the user via the Read tool so they can see it.
Also check the browser console for errors:
$B console
Note any red errors in the console output.
If BROWSE is NOT_FOUND: skip screenshots. Work from the error message and code context only.
Step 3 — Diagnose in plain English
Follow the jargon rules in lib/plain-language.md when diagnosing — no technical terms.
Write ONE sentence that describes exactly what's wrong. No technical jargon. Examples:
- "The submit button isn't working because it's pointing to a page that doesn't exist yet."
- "The page looks blank because there's an error in the data it's trying to load."
- "The layout is broken because a piece of the page is missing a required setting."
- "The image isn't showing up because the file path has a typo."
- "The login isn't working because the connection to your database timed out."
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 · 146 lines · 47 tokens per session scan A a0d65a803553
ds-unstuck is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 1,207 once invoked, about $0.0002 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.