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/chris-peterson/beacon/agents-mdgit clone --depth 1 https://github.com/chris-peterson/beaconWrote 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/chris-peterson/beacon/agents-md)<a href="https://agentmods.dev/instructions/chris-peterson/beacon/agents-md"><img src="https://agentmods.dev/badge/instructions/chris-peterson/beacon/agents-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 | $0.07971 | $0.07971 |
| Opus 5 | $0.03986 | $0.03986 |
| Sonnet 5 | $0.01594 | $0.01594 |
| Haiku 4.5 | $0.00797 | $0.00797 |
Grade B, and why
beacon AGENTS.md scanned grade B 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Claude Code status line (STATUSLINE-01/02/03)** — footer rows Claude Code renders from `beacon statusline` (wired into `~/.claude/settings.json` by `install`, which writes that one key and never replaces a `statusLin How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
beacon
Notes for AI coding agents working on beacon. Behavioral spec is SPEC.md (published to the docs site as /spec); user-facing docs are README.md. When the spec and the code disagree, ask — don't silently choose one.
What beacon is
A Claude Code plugin + sourceable zsh snippet + standalone CLI that surfaces session state two ways: a terminal-agnostic sessions view (wip / watch / serve, optionally kept always-on via beacon serve install) that reads across all sessions and paints no pane, and an iTerm2 per-pane render adapter (a status bar with action buttons, the tab color + two-line label, the window title; the badge is opt-in) for scanning concurrent panes without focusing each. Clicking a session in the dashboard raises its iTerm2 window (serve's POST /focus → beacon-iterm focus). Both read the same per-session state files — the single source of record; neither inverts that into a daemon. The sessions view works in any terminal; the iTerm2 adapter needs macOS + iTerm2.
Three deliverables, hard boundaries
| Deliverable | Path | Owns |
|---|---|---|
| CLI | bin/beacon-iterm |
Translating subcommands to iTerm2 control operations — OSC sequences for painted surfaces, Apple Events (focus to raise a window, set-name to set the window title). Stateless. No Claude awareness. |
| Plugin | scripts/beacon, hooks/, commands/, rules/ |
Hook handlers, COR resolver for signals, slash command. rules/ holds ambient rules emitted at SessionStart by hooks/emit-rules.sh (e.g. keep-session-labeled — proactive task upkeep so the sessions view has signal standalone). Invokes the CLI for every iTerm2 write. |
| Shell | shell/beacon.zsh |
Project name / branch / cwd — refreshed every prompt. Emits its own SetUserVar OSC by raw printf; calls the CLI for set-name. Never goes through the plugin. |
The plugin and shell write to disjoint user-var slots so they never overwrite each other. Don't blur this boundary.
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.
- today Changed · +18 lines · +1,181 tokens per session c1fae29e6b18
- 3d ago First seen · 132 lines · 6,790 tokens per session scan B d9011ad07ae0
beacon AGENTS.md is an instructions file published in the GitHub repository chris-peterson/beacon (1 stars, last pushed today), licensed MIT. It adds 7,971 tokens to every session, about $0.0399 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
super-backlog CLAUDE.md
Instructions for adam-s-k-i/super-backlog: This project uses the combined Backlog.md + Superpowers workflow. Read the integration block in AGENTS.md (section between SUPER-BACKLOG markers) and follow it. Tasks are managed exclusively through the backlog CLI.
docs-cockpit AGENTS.md
AGENTS.md instructions for Guohao1020/docs-cockpit, covering agents.md, what this repo is, common commands, local development and tests.
super-backlog AGENTS.md
Instructions for adam-s-k-i/super-backlog, covering backlog.md workflow, workflow system, pipeline (follow in order), binding rules and git and delivery rules (project-specific, binding).
docs-cockpit CLAUDE.md
Claude Code instructions for Guohao1020/docs-cockpit, covering claude.md, what this repo is, common commands, local development and tests.
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.