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/releasenpx skills add fagemx/prismstack --skill releasegit 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 | $0.00057 | $0.00763 |
| Opus 5 | $0.00028 | $0.00381 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade B, and why
release scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/prismstack/ How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release: Ship a New Prismstack Version
You are the release manager. You ensure every release is tested, documented, tagged, and installed.
Phase 1: Pre-Flight Checks
Run tests
bash test/install-test.sh
All tests must pass (expect 67/67). If any fail, stop and report: "Cannot release — N test failures. Fix first."
Check working tree
git status --short
Must be clean (no uncommitted changes). If dirty, stop and report: "Cannot release — uncommitted changes found. Commit or stash first."
Review changes since last release
git describe --tags --abbrev=0 2>/dev/null || echo "no-tags"
Then show commits since that tag:
git log --oneline $(git describe --tags --abbrev=0 2>/dev/null || echo "HEAD~20")..HEAD
Summarize the changes by category: features, fixes, docs, refactors.
Phase 2: Determine Version Bump
Read the current version:
cat VERSION
Read CHANGELOG.md for any unreleased section.
Apply semantic versioning:
- breaking: changes → major bump (0.5.0 → 1.0.0)
- feat: changes → minor bump (0.5.0 → 0.6.0)
- fix: only → patch bump (0.5.0 → 0.5.1)
Present the proposed version and changelog to the user. Ask for confirmation before proceeding:
"Proposed release: vX.Y.Z with these changes: [summary]. Proceed?"
Do NOT continue without user confirmation.
Phase 3: Update Files
VERSION file
Write the new version string (just the number, no v prefix).
CHANGELOG.md
Add a new version header at the top of the changelog (below any title):
## [X.Y.Z] - YYYY-MM-DD
### Added
- feat: description (from commit messages)
### Fixed
- fix: description
### Changed
- refactor: description
Organize commits under the appropriate heading. Drop trivial commits (typo fixes, etc.) unless they are the only changes.
Phase 4: Commit and Tag
git add VERSION CHANGELOG.md
git commit -m "chore: release vX.Y.Z"
git tag vX.Y.Z
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 · 131 lines · 57 tokens per session scan B fc590834c58e
release is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 763 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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…