agentmods.dev

behold AGENTS.md

Project instructions for Behold, a local-first Markdown viewer for presenting agent work, collecting browser comments, and optionally publishing fixed public snapshots.

In plain words
What is it for?
Use them when modifying Behold's viewer, local server, review storage, MCP connection, or Cloudflare publishing code.
Why use it?
They give an agent the project structure and rules it must preserve when changing Behold.

Instructions file for CodexOpenCode

11 8d ago A scan 1,116 tokens original MIT
View the source file kitlangton/behold
Install

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.

agentmods
npx agentmods add instructions/kitlangton/behold/agents-md
Clone the repo
git clone --depth 1 https://github.com/kitlangton/behold

Made for: Codex, OpenCode.

Per session 1,116 This file is loaded in full into every session.
When invoked 1,116 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01116 $0.01116
Opus 5 $0.00558 $0.00558
Sonnet 5 $0.00223 $0.00223
Haiku 4.5 $0.00112 $0.00112

Measured 2d ago against content hash 1ff2adac5e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

behold 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 2d 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Behold

Behold is a local-first Markdown viewer for presenting agent work, collecting browser comments, and optionally publishing frozen public snapshots.

Architecture

  • src/App.tsx: Solid viewer and annotation UI
  • src/lib/document-viewer.ts: browser Effect v4 HTTP client
  • shared/document-contracts.ts: shared local API response schemas
  • server/document-reviews.ts: revisions, comments, feedback cursors, and JSON persistence
  • server/document-api.ts: local HTTP and SSE adapter
  • server/local-viewer.ts: packaged asset and API server
  • server/mcp-main.ts: Effect v4 stdio MCP client for the local HTTP API
  • cloudflare/worker.ts: public Cloudflare Worker serving the built viewer, publish/list/get snapshot API, and published page shells from R2

Vite mounts the local API during development. The packaged daemon serves built assets directly. Both use the same DocumentReviews service, and the MCP process never accesses persistence directly.

Invariants

  • Local authoring and public publishing are separate systems.
  • The local viewer process is the sole owner of in-memory state, persistence, SSE clients, and long-poll waiters.
  • Package root locates executable assets; invocation cwd supplies project .env and .env.local configuration.
  • Runtime reuse requires matching package, assets, and configuration roots.
  • Public snapshots and manifests must never expose local filesystem paths.
  • Reposting a filePath updates the same hosted document id.
  • Deleting a local document never deletes an independently published snapshot.
  • Hosted documents retain a local publication receipt; startup reconciliation updates its remote status without treating network failure as deletion.
  • Document updates retain the current revision plus 20 previous revisions.
  • wait_for_feedback currently reads and acknowledges feedback in one MCP call.

Agent Surface

MCP tools:

  • host_document
  • update_document
  • get_document
  • list_documents
  • list_document_versions
  • diff_document_versions
  • wait_for_feedback
  • set_comment_status
  • delete_document
  • get_agent_guide

Read the full file on GitHub · 119 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. 2d ago First seen · 119 lines · 1,116 tokens per session scan A 1ff2adac5e18

Subscribe to this mod's changes

behold AGENTS.md is an instructions file published in the GitHub repository kitlangton/behold (11 stars, last pushed 8d ago), licensed MIT. It adds 1,116 tokens to every session, about $0.0056 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 2026-08-30.

Browser automationCode reviewDevOps and cloudcloudflare-workersmarkdownmcpsolidjs
Related

Other instructions, from other repositories

claude-chat-exporter CLAUDE.md

Instructions for agarwalvishal/claude-chat-exporter, covering claude.md, what this is, core design decision, how the export works and the install page & bookmarklet (docs/index.html).

agarwalvishal/claude-chat-exporter · 4,543 tokens

AI-MarkDone copilot-instructions.md

Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.

zhaoliangbin42/AI-MarkDone · 1,337 tokens

snag AGENTS.md

Instructions for p3bot/snag, covering agents.md, project overview, setup commands, clone repository and install dependencies.

p3bot/snag · 4,723 tokens

AI-MarkDone AGENTS.md

Instructions for zhaoliangbin42/AI-MarkDone, covering ai-markdone engineering guide, project facts, read order, common commands and non-negotiables.

zhaoliangbin42/AI-MarkDone · 1,351 tokens

markview CLAUDE.md

Instructions for paulhkang94/markview, covering markview — ai development guide, quick reference, architecture, mcp tools (for ai integration) and safety rules.

paulhkang94/markview · 1,604 tokens

mdread CLAUDE.md

Instructions for techjewel/mdread, covering claude.md, what this is, commands, architecture and styles (scss).

techjewel/mdread · 3,109 tokens