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/kouko/redshift-comment-mcp/redshift-setupnpx skills add kouko/redshift-comment-mcp --skill redshift-setupgit clone --depth 1 https://github.com/kouko/redshift-comment-mcpWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/skills/kouko/redshift-comment-mcp/redshift-setup)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 | $0.00149 | $0.03483 |
| Opus 5 | $0.00075 | $0.01741 |
| Sonnet 5 | $0.00030 | $0.00697 |
| Haiku 4.5 | $0.00015 | $0.00348 |
Grade A, and why
redshift-setup 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 3d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redshift Setup
Drives the connection-profile setup for the redshift-comment-mcp plugin
through a chat conversation, with one critical security boundary:
the password is collected in the user's own terminal, not in chat,
because anything typed into Claude conversation lives in the conversation
history forever (per domain-teams:skill-team / standards/user-terminal-handoff.md).
When to Use
- User invokes
/redshift-setup(default form — single cluster, profile namedefault) - User invokes
/redshift-setup <name>(named form — multi-cluster, picks a custom profile name) - User says "set up Redshift" / "configure my Redshift connection" / "幫我設定 Redshift" / "Redshift の接続を設定して" or similar
- User wants to add a second / third connection profile alongside existing ones
When NOT to Use
- User wants to switch between already-configured profiles without
re-typing connection fields → use
/redshift-comment-mcp:redshift-switch-profileinstead. This skill always re-collects host / user / dbname / password (overkill for a pure switch and risks corrupting the keychain entry on password typo). - User wants to change ONLY the password of an existing profile → use the
one-liner
uvx --from "git+https://github.com/kouko/redshift-comment-mcp.git" redshift-comment-mcp set-password --profile <name>instead; this skill is overkill. - User wants to delete a profile → use
delete-profilesubcommand directly.
Inputs
| Invocation | Profile name resolved to | active-profile pointer effect |
|---|---|---|
/redshift-setup (no default profile yet) |
default (silent — no Q1) |
none (clean single-profile state) |
/redshift-setup (default already exists) |
ask user: (a) overwrite default OR (b) pick a new name |
(a) Branch A no-op / (b) Branch B asks |
/redshift-setup <name> |
<name> (validated ^[A-Za-z0-9_-]+$) |
Branch A writes / Branch B asks |
Storage Model
| Field | Where it goes |
|---|---|
| host / port / user / dbname | ~/.config/redshift-comment-mcp/config.toml (mode 600) under [profile.<name>] |
| password | OS keychain (macOS Keychain / Windows Credential Locker / Linux Secret Service), service redshift-comment-mcp, account <profile-name> |
| active profile selection (which one MCP server uses) | ~/.config/redshift-comment-mcp/active-profile (one-line text, mode 600). Absent file ↔ server uses "default" — single-profile users never see this file. |
What ships with it
3 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.
- 3d ago First seen · 358 lines · 149 tokens per session scan A 32c3b9cff82a
redshift-setup is a skill published in the GitHub repository kouko/redshift-comment-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session and 3,483 once invoked, about $0.0007 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
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
moderator-page-migration
Port a moderator page from the main Next.js app (src/pages/moderator/) into apps/moderator. Use when asked to migrate, move or cut over a /moderator/ page to the spoke, or to port its tRPC procedures and Prisma services to SvelteKit loads/actions and Kysely.
prisma-upgrade-v7
Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
sqlitecpp-update-sqlite
How to update the bundled SQLite3 amalgamation (sqlite3/sqlite3.c and sqlite3.h), the Meson wrap, README.md, and CHANGELOG.md. Use when upgrading SQLite, refreshing the vendored amalgamation, or bumping the sqlite3 wrap.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK…