releases-cli: Instructions file for Codex

AGENTS.md

releases-cli AGENTS.md is an instructions file for Codex, OpenCode from buildinternet/releases-cli. It costs 5,382 tokens per session, scanned A, original, MIT.

A repository instruction guide for Releases CLI, a command-line program that reads from the Releases registry through a web API. It documents the TypeScript and Bun setup, commands, project structure, and development rules; a monorepo is a single repository that contains multiple related projects.

In plain words
What is it for?
Use it when developing, checking, testing, or building Releases CLI. It covers running commands from source, compiling the Bun executable, linting and type-checking, and understanding where the CLI and API client code belong.
Why use it?
It gives coding agents the local conventions needed to work safely in this repository. It also makes clear that the CLI uses a remote API rather than a local database.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions Claude Code.

This is buildinternet/releases-cli's own configuration. It tells Codex and OpenCode how to work on releases-cli 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 releases-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to buildinternet/releases-cli. 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/buildinternet/releases-cli/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/buildinternet/releases-cli

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 releases-cli AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/buildinternet/releases-cli/agents-md/github.svg)](https://agentmods.dev/instructions/buildinternet/releases-cli/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/buildinternet/releases-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/buildinternet/releases-cli/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 releases-cli AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/buildinternet/releases-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/buildinternet/releases-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,382 This file is loaded in full into every session.
When invoked 5,382 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 $0.05382 $0.05382
Opus 5.5 $0.02153 $0.02153
Sonnet 5.5 $0.01076 $0.01076
Haiku 4.5 $0.00538 $0.00538

Measured 11d ago against content hash e50d25802e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

releases-cli 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 11d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents guide — releases-cli

This repo is the public, client-only CLI for the Releases registry. It talks to api.releases.sh over HTTP. Ingest, database access, and AI pipelines live in a separate open-source backend monorepo, buildinternet/releases.

Stack

  • Runtime: Bun (required for bun --compile)
  • Language: TypeScript (strict mode)
  • CLI: Commander
  • MCP: @modelcontextprotocol/sdk on stdio
  • HTTP client: src/api/client.ts is the only data-access layer. No Drizzle, no SQLite, no local DB.

Commands

bun src/index.ts <command>    # run from source
bun run build                 # compile binary to dist/releases
bun run check                 # oxlint (lint + type-check) + oxfmt check — CI gate
bun run lint                  # oxlint only (`typecheck` is an alias)
bun test                      # bun test (not part of check)

Architecture

  • src/index.ts — entry point. Validates config, sets up telemetry, rewrites legacy aliases, hands off to Commander.
  • src/cli/program.ts — Commander program wiring. Public reader commands at the top level; operator workflows under admin.
  • src/cli/commands/ — one file per command. Every command goes through src/api/client.ts for data access.
  • src/api/client.ts — single HTTP boundary. apiFetch() auto-attaches Authorization: Bearer ${RELEASES_API_KEY} when admin mode is active, and (via src/lib/mutation-log.ts) records mutating requests when RELEASES_RUN_DIR is set.
  • src/lib/mode.ts — getApiUrl() / getApiKey() / isAdminMode() / validateConfig(). Always remote.
  • src/lib/mutation-log.ts — admin-mutation audit log for the ~/.releases/work/ maintenance workspace. When RELEASES_RUN_DIR is set, each non-GET request (minus telemetry/heartbeat plumbing) appends a {timestamp, command, target, result} JSONL line to $RELEASES_RUN_DIR/mutations.jsonl. Unset → no-op; fully fail-open.
  • src/lib/trace.ts — managed-session traces. Writes <dir>/<id>/{trace.json,summary.md} for terminal sessions/workflows; dir precedence is explicit flag > RELEASES_RUN_DIR > ~/.releases/work/runs. Used by --trace-dir (onboard, source fetch --wait, overview batch --wait) and task get --save. summary.md mirrors the monorepo's docs/architecture/maintenance-workspace.md run-summary template.
  • src/lib/telemetry.ts — anonymous usage pings to api.releases.sh/v1/telemetry. First-run notice shown once. Opt out via RELEASES_TELEMETRY_DISABLED=1 or DO_NOT_TRACK=1.
  • src/lib/update-check.ts — npm-registry poll for newer CLI versions (24h cache in ~/.releases/update-check.json). Prints a one-line stderr nag after command output when stale. src/lib/skills-update-check.ts mirrors it for the bundled skills: GitHub git/trees/main poll for the plugins/claude/releases/skills/ subtree SHA, cached in ~/.releases/skills-check.json. Baseline is written on successful releases skills install; the nag fires only if a baseline exists and diverges. Defense in depth: when the skills CLI's lock file ($XDG_STATE_HOME/skills/.skill-lock.json or ~/.agents/.skill-lock.json) is present and parses cleanly with zero buildinternet/releases-cli entries, the nag is suppressed (user uninstalled via skills). A missing/unreadable lock file falls through to the baseline check so manual installers aren't penalized. Opt out via RELEASES_DISABLE_SKILL_UPDATE_CHECK=1. Both checks skip non-TTY callers and --help/--version.
  • src/mcp/server.ts — local stdio MCP bridge. Exposes read-only tools (search, get_latest_releases, list_catalog, get_catalog_entry, get_source, list_organizations, get_organization, changelog) that proxy to api.releases.sh. Mirrors the canonical tool names served by the hosted server at mcp.releases.sh, plus changelog for recent releases.sh product updates (same as releases changelog: optional limit 1–50, default 5; JSON { url, feed, entries }; GET-only, no writes). get_catalog_entry inlines a CHANGELOG slice for source entries via include_changelog / changelog_path / changelog_offset / changelog_limit / changelog_tokens (products have none — degrades with a clear message). The former get_source_changelog tool was removed in 0.72.0 — use get_catalog_entry with the changelog_* params instead.
  • @buildinternet/releases-core — runtime-neutral helpers (schema, categories, slicing, IDs, slugs, tokens, CLI contracts). Published from the private buildinternet/releases monorepo (canonical source in packages/core/), consumed here as a regular npm dependency. Bump the pin in package.json when adopting a new schema.
  • packages/lib/ (@buildinternet/releases-lib) — logger, errors, trimmed config.
  • plugins/claude/releases/skills/ — single source of truth for the three user-facing agent skills (releases-mcp, releases-cli, analyzing-releases); there is no generated copy and no npm wrapper (@buildinternet/releases-skills is retired/deprecated). Operator skills live in the backend monorepo's .claude/skills/ tree — do not re-add copies here. They live inside the Claude plugin folder because the plugin directory screens everything under a plugin's source, and a plugin can't reference files outside its own folder — so the plugin is self-contained and .claude-plugin/marketplace.json only points source at ./plugins/claude/releases (no inline skills/commands/mcpServers; those are discovered from the plugin's own .claude-plugin/plugin.json and folder layout). npx skills add resolves the same folder through the marketplace source, so editing a skill is the whole change — nothing to re-sync. Don't move them back to the repo root: that makes the whole repo the plugin again. Cross-agent install runs through releases skills install, which shells out to npx skills add buildinternet/releases-cli (the vercel-labs/skills ecosystem). Wiring is in src/cli/commands/skills.ts; pure argv construction in src/cli/skills/build-args.ts.
  • plugins/claude/releases/ — agent plugin in the common plugin layout (listed in the Claude Code marketplace; submitted to the xAI plugin marketplace as release-notes-index, pending review; add further marketplaces as install subsections in its README without rewording the intro), self-contained: .claude-plugin/plugin.json (+ icon.svg, copied from the web app's apps/web/src/app/icon.svg in the monorepo), .mcp.json (hosted MCP, wrapped in mcpServers — the flat form loads in Claude Code but xAI's catalog scanner ignores it), commands/, skills/. Validate with claude plugin validate . from the repo root. Keep the folder path: the Claude directory listing pins plugins/claude/releases, and the xAI catalog entry will pin the same path.
  • npm/ — meta package (@buildinternet/releases) + five platform binary packages. CI writes the compiled binary into each platform package before publishing.

Read the full file on GitHub · 91 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. 11d ago Changed · +98 tokens per session e50d25802e4b
  2. 24d ago Changed · +142 tokens per session 3409d59d6782
  3. 1mo ago Changed · +52 tokens per session 188a33e0cf18
  4. 1mo ago First seen · 91 lines · 5,090 tokens per session scan A d63a00f616b6

Subscribe to this mod's changes

releases-cli AGENTS.md is an instructions file published in the GitHub repository buildinternet/releases-cli (4 stars, last pushed 11d ago), licensed MIT. It adds 5,382 tokens to every session, about $0.0215 per session on Opus 5.5. 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

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 · 9,649 tokens

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 · 7,257 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 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 · 4,159 tokens