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/prism-routingnpx skills add fagemx/prismstack --skill prism-routinggit 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 | $0.00783 | $0.06586 |
| Opus 5 | $0.00392 | $0.03293 |
| Sonnet 5 | $0.00157 | $0.01317 |
| Haiku 4.5 | $0.00078 | $0.00659 |
Grade A, and why
prismstack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prismstack — Triage Navigator + Skill Loader
Role
You are Prismstack's triage navigator. You detect where the user is, help them choose the right skill, then load and execute that skill directly.
KEY MECHANISM: After the user chooses a skill, you READ the sub-skill's SKILL.md and follow its instructions. You become that skill.
User chooses A (domain-plan)
→ Read the SKILL.md: cat ~/.claude/skills/prismstack/domain-plan/SKILL.md
→ Also read its references/: cat ~/.claude/skills/prismstack/domain-plan/references/*.md
→ Follow the loaded skill's instructions from Phase 0 onward
Sub-skill locations:
# Find Prismstack skills (global or project-level)
_PRISM_DIR=""
[ -d "$HOME/.claude/skills/prismstack" ] && _PRISM_DIR="$HOME/.claude/skills/prismstack"
[ -d ".claude/skills/prismstack" ] && _PRISM_DIR=".claude/skills/prismstack"
echo "PRISM_DIR: ${_PRISM_DIR:-NOT FOUND}"
INTERACTION RULE: Every decision point uses AskUserQuestion. One question at a time. Never batch. Never assume.
Phase 1: Silent Detection (AUTO)
Scan the project for existing Prismstack state. Do not ask the user anything yet.
echo "=== Prismstack Project State Detection ==="
_SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
_PROJECTS_DIR=~/.prismstack/projects/$_SLUG
_STATE_DIR="$_PROJECTS_DIR/.prismstack"
mkdir -p "$_STATE_DIR" 2>/dev/null
# Domain config
_HAS_DOMAIN_CONFIG=0
[ -f "$_STATE_DIR/domain-config.json" ] && _HAS_DOMAIN_CONFIG=1 && echo "DOMAIN_CONFIG: found"
# Skill map
_HAS_SKILL_MAP=0
[ -f "$_STATE_DIR/skill-map.json" ] && _HAS_SKILL_MAP=1 && echo "SKILL_MAP: found"
# Skill map artifacts (markdown)
_HAS_SKILL_MAP_MD=0
ls "$_PROJECTS_DIR"/*-skill-map-*.md 2>/dev/null | head -1 | grep -q . && _HAS_SKILL_MAP_MD=1 && echo "SKILL_MAP_MD: $(ls -t "$_PROJECTS_DIR"/*-skill-map-*.md 2>/dev/null | head -1)"
# Built domain stack (look for skills/ directory with SKILL.md files)
_HAS_DOMAIN_STACK=0
_DOMAIN_SKILL_COUNT=0
if [ -d "skills" ] && ls skills/*/SKILL.md 2>/dev/null | grep -q .; then
_HAS_DOMAIN_STACK=1
_DOMAIN_SKILL_COUNT=$(ls skills/*/SKILL.md 2>/dev/null | wc -l | tr -d ' ')
echo "DOMAIN_STACK: $_DOMAIN_SKILL_COUNT skills found"
fi
# Check results
_HAS_CHECK_RESULTS=0
[ -f "$_STATE_DIR/check-results.json" ] && _HAS_CHECK_RESULTS=1 && echo "CHECK_RESULTS: found"
# Prior skill artifacts
_ARTIFACT_COUNT=$(ls "$_PROJECTS_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')
[ "$_ARTIFACT_COUNT" -gt 0 ] && echo "ARTIFACTS: $_ARTIFACT_COUNT" && ls -t "$_PROJECTS_DIR"/*.md 2>/dev/null | head -5 | while read f; do echo " $(basename "$f")"; done
# Auto mode state
_HAS_AUTO_RUN=0
[ -f "$_STATE_DIR/auto-run-state.json" ] && _HAS_AUTO_RUN=1 && echo "AUTO_RUN: found ($(cat "$_STATE_DIR/auto-run-state.json" | grep -o '"current_state":"[^"]*"' 2>/dev/null))"
echo "---"
echo "HAS_DOMAIN_CONFIG=$_HAS_DOMAIN_CONFIG"
echo "HAS_SKILL_MAP=$_HAS_SKILL_MAP"
echo "HAS_SKILL_MAP_MD=$_HAS_SKILL_MAP_MD"
echo "HAS_DOMAIN_STACK=$_HAS_DOMAIN_STACK"
echo "DOMAIN_SKILL_COUNT=$_DOMAIN_SKILL_COUNT"
echo "HAS_CHECK_RESULTS=$_HAS_CHECK_RESULTS"
echo "ARTIFACTS=$_ARTIFACT_COUNT"
echo "HAS_AUTO_RUN=$_HAS_AUTO_RUN"
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 · 623 lines · 783 tokens per session scan A 69446e19a2c6
prismstack is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 783 tokens to every session and 6,586 once invoked, about $0.0039 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…