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/fagemx/prismstack/skill-devnpx skills add fagemx/prismstack --skill skill-devgit clone --depth 1 https://github.com/fagemx/prismstackWhat 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 | $0.00064 | $0.00965 |
| Opus 5 | $0.00032 | $0.00483 |
| Sonnet 5 | $0.00013 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
skill-dev 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skill-dev: Develop Prismstack Product Skills
You are a Prismstack skill developer. You modify the 10 product skills with discipline, ensuring every change follows the methodology.
Phase 0: Scope the Change
Parse $ARGUMENTS for the target skill and change description.
If not provided, ask:
- Which skill? (one of the 10 product skills in
skills/*/SKILL.md) - What change? (add feature, fix issue, refactor section, etc.)
Read the current SKILL.md for the target skill fully before making any change.
Phase 1: Load Relevant Methodology
Based on the type of change, read the appropriate methodology file:
| Change Type | Read This |
|---|---|
| Structure / sections | skills/shared/methodology/skill-craft-guide.md |
| Scoring / rubric | skills/shared/methodology/quality-standards.md |
| Artifact flow / wiring | skills/shared/methodology/system-wiring-guide.md |
| Fix loop / triage | skills/shared/methodology/fix-loop-guide.md |
| Context / accumulation | skills/shared/methodology/context-accumulation-guide.md |
If the change spans multiple areas, read all relevant files. Do not guess at methodology — read it.
Phase 2: Make the Change
Rules for editing:
- Minimal and surgical. Change only what is needed. Do not rewrite surrounding sections.
- Read before edit. Always use Read tool on the file before using Edit tool. Never edit blind.
- Preserve voice. Match the existing tone and formatting of the skill.
- No scope creep. If you notice other issues while editing, note them but do not fix them now. One change per /skill-dev invocation.
Use the Edit tool (not Write) for modifications. Write is only for new files.
Phase 3: Self-Check (Quick 15D)
After the edit, run a quick quality check on the modified skill:
- Read
skills/shared/methodology/quality-standards.mdfor the 15D rubric - Score the modified skill on all 15 dimensions (1-5 scale)
- Compare to a rough pre-edit baseline (your reading from Phase 0)
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 · 97 lines · 64 tokens per session scan A 0d4708805a18
skill-dev is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 965 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
ebay-sold-listings-search
All process output to user (progress updates, process notifications) follows the user's language.
youtube-channel-business-email
YouTube channel business email and contact extractor: accepts a channel id (UCxxx), handle (@name), or URL; navigates the channel About view; extracts the business email from the description text plus full channel metadata (name, id, country, subscriber count, view count, video count, joined date, external links…
webcrawler-deep-crawl
Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape…
1688-product-detail
Extracts comprehensive wholesale product data from 1688.com product detail pages: title, tiered pricing, SKU variants with dimensions/weight, product images, seller info, shop scores, buyer protection, cross-border flags, product attributes, coupon/promotion data, and review stats. Use when user mentions 1688…
amazon-listing-competitor-analysis-skill
This skill helps users analyze Amazon competitor listings by ASIN and produce structured competitive intelligence plus strategic opportunity points for their own go-to-market. The Agent should proactively apply this skill when users want to analyze a competitor Amazon listing by ASIN, understand what a top-ranked…
amazon-product-detail
Amazon product detail page scraper: extract full product data from any open Amazon product detail URL (any /dp/{asin} or /gp/product/{asin} page across all Amazon regional TLDs) — returns asin, url, title, brand, price, listPrice, stars, reviewsCount, starsBreakdown (5/4/3/2/1 star percentages), answeredQuestions…