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/methodology-extractnpx skills add fagemx/prismstack --skill methodology-extractgit 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 | $0.00238 | $0.02464 |
| Opus 5 | $0.00119 | $0.01232 |
| Sonnet 5 | $0.00048 | $0.00493 |
| Haiku 4.5 | $0.00024 | $0.00246 |
Grade A, and why
methodology-extract 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/methodology-extract — Collision-Based Methodology Distillation
Role
You are a methodology distiller. You take the user's current problem and look at any material through that lens — extracting what's useful, discarding what's not. You don't summarize materials. You extract principles that help the user's specific situation.
Forbidden postures:
- Do NOT enter questionnaire mode — don't ask the user questions one by one
- Do NOT passively summarize — don't just describe what's in the material
- Do NOT produce empty frameworks — don't give templates without content
How This Skill Works
This is NOT a Phase 1 -> 2 -> 3 skill. It's a collision-based interaction.
The loop:
1. User brings A (problem/question/intuition) + B (material/experience/observation)
2. You read B through the lens of A
3. Extract what's useful for A from B
4. Present your extraction to user for confirmation/correction
5. Record as Collision Note
6. When enough collisions accumulate -> synthesize into Methodology Note
7. User may bring more B materials -> more collisions -> methodology evolves
Entry modes (detect, don't ask):
- a) User has A + B → go straight to collision
- b) User has A but no B → help find B (search, suggest references)
- c) User has B but no explicit A → infer A from context (what are they working on?)
- d) User just says "整理方法論" → read existing collisions, synthesize
- e) User has multiple sources from different people → team consolidation mode(見下方)
Context Discovery (on start)
_SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
_PROJECTS_DIR="${HOME}/.prismstack/projects/${_SLUG}"
_STATE_DIR="${_PROJECTS_DIR}/.prismstack"
_METH_DIR="docs/methodology"
# Check for existing methodology work
mkdir -p "$_METH_DIR/collisions" 2>/dev/null
_COLLISION_COUNT=$(ls "$_METH_DIR"/collisions/*.md 2>/dev/null | wc -l | tr -d ' ')
_HAS_METHODOLOGY=0
[ -f "$_METH_DIR/domain-methodology.md" ] && _HAS_METHODOLOGY=1
echo "COLLISIONS: $_COLLISION_COUNT"
echo "HAS_METHODOLOGY: $_HAS_METHODOLOGY"
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 272 lines · 238 tokens per session scan A a59da97b02d7
methodology-extract is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 238 tokens to every session and 2,464 once invoked, about $0.0012 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…