bluesky-mcp: Instructions file for Codex

AGENTS.md

bluesky-mcp AGENTS.md is an instructions file for Codex, OpenCode from coilyco-flight-deck/bluesky-mcp. It costs 645 tokens per session, scanned A, original, MIT.

Repository instructions for a TypeScript MCP server, a program that lets AI tools access selected services through a standard interface. The server provides authenticated, read-only Bluesky access over HTTP.

In plain words
What is it for?
Guiding development commands, tests, source changes, tool inventory, data handling, and deployment boundaries in the Bluesky MCP repository.
Why use it?
It sets project boundaries and safety rules, including which tools are allowed and how credentials must be protected.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is coilyco-flight-deck/bluesky-mcp's own configuration. It tells Codex and OpenCode how to work on bluesky-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bluesky-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to coilyco-flight-deck/bluesky-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/coilyco-flight-deck/bluesky-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/coilyco-flight-deck/bluesky-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for bluesky-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coilyco-flight-deck/bluesky-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/coilyco-flight-deck/bluesky-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/coilyco-flight-deck/bluesky-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/coilyco-flight-deck/bluesky-mcp/agents-md/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.

agentmods 80×15 button for bluesky-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/coilyco-flight-deck/bluesky-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/coilyco-flight-deck/bluesky-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 645 This file is loaded in full into every session.
When invoked 645 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00645 $0.00645
Opus 5 $0.00322 $0.00322
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00064 $0.00064

Measured 8d ago against content hash d95c71b5c31f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bluesky-mcp AGENTS.md 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 8d 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.

AGENTS.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions

Scope

bluesky-mcp is one TypeScript process that exposes Kai's authenticated Bluesky reads over streamable HTTP. It is intentionally a finite, read-only adapter. There is no frontend, database, generic network proxy, or mutation surface.

Project shape

The MCP server is TypeScript under src/, built to dist/. src/icon.ts carries the service icon, and scripts/ holds the shell and Python that CI steps invoke on one line.

Repo boundaries

This repository owns source, tests, image construction, and image publishing. Deployment manifests, secret mappings, external access policy, and rollout automation belong only in coilyco-bridge/deploy.

Commands

Run development commands through ward using the verbs in .ward/ward.yaml. Do not put credentials, session values, deployment hostnames, or infrastructure details in tracked files or logs.

Safety

  • Keep the reviewed 11-tool inventory exact and read-only.
  • Do not add arbitrary XRPC, URL, raw HTTP, login, session, or record tools.
  • The app password and SDK session tokens must remain process-local and be redacted from all returned values and errors.
  • Preserve bounded page sizes, post batch size, and thread depth.

Validation

Run just lint, just typecheck, just test, ward audit, and ward precommit before landing source changes.

Cross-repo contracts

The catalog pre-commit hooks are authored in agentic-os and consumed here by upstream rev, never forked. Deployment policy, pull credentials, and secret mapping are owned by deploy, not here.

Agent rules

Use she/her for Kai. No em dashes, italics, or semicolons in prose. Name the actor in every action sentence.

Release

After validation, main CI publishes the private image forgejo.coilysiren.me/coilyco-flight-deck/bluesky-mcp:<full-source-sha> through the trusted deploy lane. The runner supplies REGISTRY_TOKEN for package writes. coilyco-bridge/deploy owns the separate read-only forgejo-registry pull credential and rollout.

Read the full file on GitHub · 79 lines

Changes

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.

  1. 8d ago First seen · 79 lines · 645 tokens per session scan A d95c71b5c31f

Subscribe to this mod's changes

bluesky-mcp AGENTS.md is an instructions file published in the GitHub repository coilyco-flight-deck/bluesky-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 645 tokens to every session, about $0.0032 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens