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 skills add alexpolonsky/agent-skill-jlm-coffee --skill agent-skill-jlm-coffeegit clone --depth 1 https://github.com/alexpolonsky/agent-skill-jlm-coffeeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alexpolonsky/agent-skill-jlm-coffee/agent-skill-jlm-coffee)<a href="https://agentmods.dev/skills/alexpolonsky/agent-skill-jlm-coffee/agent-skill-jlm-coffee"><img src="https://agentmods.dev/badge/skills/alexpolonsky/agent-skill-jlm-coffee/agent-skill-jlm-coffee/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alexpolonsky/agent-skill-jlm-coffee/agent-skill-jlm-coffee"><img src="https://agentmods.dev/badge/skills/alexpolonsky/agent-skill-jlm-coffee/agent-skill-jlm-coffee.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00081 | $0.01219 |
| Opus 5.5 | $0.00032 | $0.00488 |
| Sonnet 5.5 | $0.00016 | $0.00244 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
jlm-coffee scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **No dependencies**: Python stdlib only (urllib, json) How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jerusalem Coffee Finder
Search specialty coffee shops in Jerusalem - ratings, amenities, opening hours, reviews, and locations from coffee.amsterdamski.com, created and curated by Shaul Amsterdamski (@amsterdamski2).
Data from the official public JSON export provided by the site maintainer. May not reflect current status. Provided "as is" without warranty of any kind.
Quick Start
# List all coffee shops
python3 {baseDir}/scripts/jlm-coffee.py list
# Find a shop by name
python3 {baseDir}/scripts/jlm-coffee.py search "סיבריס"
Commands
| Command | Description |
|---|---|
list |
List all approved specialty coffee shops |
search <query> |
Search shops by name (Hebrew or English) |
get <id_or_name> |
Get full details for a specific shop |
filter <amenity> |
Filter shops by amenity (wifi, dogs, kosher, etc.) |
open-now |
Show shops currently open |
amenities |
List all available amenity filters |
surprise |
Pick a random coffee shop (prefers open ones) |
Search and Filter Examples
# Search by name (Hebrew or English)
python3 {baseDir}/scripts/jlm-coffee.py search "רוסטרס"
python3 {baseDir}/scripts/jlm-coffee.py search "Cafe Pepa"
# Filter by amenity
python3 {baseDir}/scripts/jlm-coffee.py filter wifi
python3 {baseDir}/scripts/jlm-coffee.py filter dogs
python3 {baseDir}/scripts/jlm-coffee.py filter kosher
python3 {baseDir}/scripts/jlm-coffee.py filter laptop
# Shops open right now
python3 {baseDir}/scripts/jlm-coffee.py open-now
# Full details for a shop
python3 {baseDir}/scripts/jlm-coffee.py get "בארוק"
python3 {baseDir}/scripts/jlm-coffee.py get EljFiggwObssQpypWMf0
Options Reference
| Option | Commands | Description |
|---|---|---|
--json |
all | Output in JSON format (agent-friendly) |
--no-color |
all | Disable colored output (auto-detected for non-TTY) |
What ships with it
1 file 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.
- 1mo ago First seen · 115 lines · 81 tokens per session scan A 82e267b9a4ae
jlm-coffee is a skill published in the GitHub repository alexpolonsky/agent-skill-jlm-coffee (1 stars, last pushed 8mo ago), licensed MIT. It adds 81 tokens to every session and 1,219 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ontopo
Find restaurants and check table availability in Israel. Search across multiple dates and venues at once, view menus, and get a booking link to finish on Ontopo. Covers dining and restaurant discovery in Tel Aviv, Jerusalem, Haifa, Eilat and 23 more cities. Use for "restaurant reservation", "table booking", "book a…
maccabi-pharm-search
Search for medications and check real-time stock availability at Maccabi pharmacies in Israel. Use when searching for drugs like "nurofen", "acamol/אקמול", "advil", or finding nearby pharmacy branches with stock. Supports Hebrew and English drug names. מכבי פארם, תרופות, מלאי, בית מרקחת.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…