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 instructions/kouko/redshift-comment-mcp/claude-mdgit clone --depth 1 https://github.com/kouko/redshift-comment-mcpWrote 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/instructions/kouko/redshift-comment-mcp/claude-md)<a href="https://agentmods.dev/instructions/kouko/redshift-comment-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kouko/redshift-comment-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01277 | $0.01277 |
| Opus 5 | $0.00639 | $0.00639 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
redshift-comment-mcp CLAUDE.md 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 4d 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.
curl -s https://pypi.org/pypi/redshift-comment-mcp/X.Y.Z/json | jq .info.version How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project guidance for Claude Code
Conventions and pitfalls specific to this repo. The global preferences
in ~/.claude/CLAUDE.md still apply; this file overrides or adds to
them where the project's needs differ.
Version bumping (MUST)
This plugin has two version fields that must move together. Forgetting either ships an inconsistent release:
.claude-plugin/plugin.json—"version"field (Claude Code plugin marketplace + install UI read this)pyproject.toml—[tool.setuptools_scm]fallback_versionfield (the sourceuv run/pip installsee when there is no.gitdirectory, e.g. Claude Code's plugin cache install path)
When to bump (pick one per release, semver):
| Change shape | Bump |
|---|---|
| Backward-incompatible signature change, removed tool, breaking config / format change | MAJOR (0.x.y → (x+1).0.0 while pre-1.0, semantically still "breaking") |
New tool, new field on a tool response, new skill, new server instructions directive, additive behavior |
MINOR (x.y.z → x.(y+1).0) |
| Bug fix, doc fix, test-only change | PATCH (x.y.z → x.y.(z+1)) |
Tests-only / docs-only / chore commits can ride the next feature bump — don't open a PR just to bump for a doc typo.
Bundle accumulated changes if needed. If multiple MINOR / PATCH-level
PRs have merged since the last bump without one, the next bump rolls them
all up under the highest applicable level. Example: three PATCHes plus
one MINOR since 0.4.0 → ship 0.5.0 (MINOR shadows PATCH).
Always bump on the same PR as the user-visible change. Splitting the bump into a separate "release" PR loses the correlation (which PR introduced which feature) and risks shipping unbumped code if the bump PR slips. The only acceptable exception: chore PRs that have no user-visible effect.
Release publishing (MUST)
Bumping the two version fields is not shipping. The plugin path
(claude plugin install) runs from cloned-repo source, so it sees the
bump the moment the PR merges. The PyPI path (used by Claude Desktop +
other MCP clients via uvx redshift-comment-mcp) only updates when
these three steps run after the bump PR merges to main:
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.
- 4d ago First seen · 112 lines · 1,277 tokens per session scan A 457057307144
redshift-comment-mcp CLAUDE.md is an instructions file published in the GitHub repository kouko/redshift-comment-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,277 tokens to every session, about $0.0064 per session on Opus 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.