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/harshii0509/designstack/statsnpx skills add harshii0509/designStack --skill statsgit clone --depth 1 https://github.com/harshii0509/designStackWhat 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 | $0.00044 | $0.00892 |
| Opus 5 | $0.00022 | $0.00446 |
| Sonnet 5 | $0.00009 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
ds-stats scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
_DESIGNSTACK_VER="0.1.0"
_ANALYTICS="$HOME/.dstack/analytics/skill-usage.jsonl"
_TEL_CONFIG="$HOME/.dstack/config"
_TEL=$(grep "^telemetry=" "$_TEL_CONFIG" 2>/dev/null | cut -d= -f2 || echo "community")
_HAS_DATA="no"
[ -f "$_ANALYTICS" ] && [ -s "$_ANALYTICS" ] && _HAS_DATA="yes"
_TOTAL=$(wc -l < "$_ANALYTICS" 2>/dev/null | tr -d ' ' || echo "0")
echo "DESIGNSTACK: $_DESIGNSTACK_VER"
echo "TELEMETRY: $_TEL"
echo "HAS_DATA: $_HAS_DATA"
echo "TOTAL_RUNS: $_TOTAL"
echo "ANALYTICS_FILE: $_ANALYTICS"
What this skill does
Show how you've used designStack — which skills you run most, how many succeeded, and when you last used each one.
Step 1 — Check telemetry status
If TELEMETRY is off:
"Analytics is turned off — no data has been collected. To enable it, edit
~/.dstack/configand changetelemetry=offtotelemetry=community. Future skill runs will be tracked from that point."
Stop here if telemetry is off.
If HAS_DATA is no:
"No usage data yet — run a few designStack skills first and then come back. Analytics are stored in
~/.dstack/analytics/skill-usage.jsonl."
Stop here if no data.
Step 2 — Read the analytics file
Run this bash to extract usage data:
# Count per skill
awk -F'"' '/"skill":/ {for(i=1;i<=NF;i++) if($i=="skill") print $(i+2)}' "$HOME/.dstack/analytics/skill-usage.jsonl" | sort | uniq -c | sort -rn
# Count by outcome
awk -F'"' '/"outcome":/ {for(i=1;i<=NF;i++) if($i=="outcome") print $(i+2)}' "$HOME/.dstack/analytics/skill-usage.jsonl" | sort | uniq -c
# Last 5 runs (most recent)
tail -5 "$HOME/.dstack/analytics/skill-usage.jsonl"
Step 3 — Show the report
Present a plain-English summary:
designStack usage so far
Total skill runs: [TOTAL_RUNS]
Most used skills: [For each skill in usage count order:]
/ds-[skill]— used [N] times
Outcomes:
- Success: [N] ([X]%)
- Error/abort: [N] ([Y]%)
Last 5 sessions: [For each of last 5 entries — show skill name + outcome + timestamp in plain English, e.g. "ran /ds-look · success · 2 days ago"]
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 · 96 lines · 44 tokens per session scan A b023551e2474
ds-stats is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 892 once invoked, about $0.0002 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
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…