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/junchenmeteor/agentshot/agents-mdgit clone --depth 1 https://github.com/JunchenMeteor/AgentShotWhat 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 | $0.01266 | $0.01266 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
AgentShot 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentShot Agent Guide
This file is for AI coding agents working on AgentShot.
Project Summary
AgentShot is a local-first screenshot bridge for terminal AI agents. It helps users capture or copy a screenshot, save it as a local image file, render an AI-tool-specific prompt that references the image path, and copy that prompt to the clipboard.
The primary user workflow is:
install AgentShot -> daemon watches clipboard -> user takes screenshot -> AgentShot saves image and copies prompt -> user pastes into Claude Code, Codex CLI, or another terminal AI tool
AgentShot should not upload screenshots, call AI APIs, or inject text into terminal windows by default.
Product Direction
Primary distribution is npm:
npm install -g jcagentshot
The package uses postinstall only to print daemon setup guidance. It must not start background processes or register startup services during package installation.
Current product phases:
- Robust local screenshot bridge.
- Resident startup daemon by default.
- Read-only AI session detection for future explicit injection workflows.
Direct terminal injection is not a default behavior. Keep the safe default as "copy prompt to clipboard, user pastes manually".
Tech Stack
- Runtime: Node.js 18+
- Module system: ESM
- CLI entrypoint:
bin/agentshot.js - Tests: Node built-in test runner
- Package manager: npm
- Platforms: Windows and macOS first, limited Linux clipboard fallback
- No runtime npm dependencies currently
Important Files
bin/agentshot.js: main CLI implementation.scripts/postinstall.mjs: npm postinstall guidance. It must not start the daemon.scripts/validate.mjs: local validation runner.tests/agentshot.test.js: unit tests.README.md: English user-facing README.README.zh-CN.md: Chinese user-facing README.docs/PRODUCT_SPEC.md: product scope, platform strategy, and roadmap.docs/NPM_RELEASE.md: npm publishing checklist.docs/QUALITY.md: quality and validation baseline.
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.
- yesterday First seen · 211 lines · 1,266 tokens per session scan A 4a8a087b812e
AgentShot AGENTS.md is an instructions file published in the GitHub repository JunchenMeteor/AgentShot (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,266 tokens to every session, about $0.0063 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.
Other instructions, from other repositories
snip CLAUDE.md
Instructions for edouard-claude/snip, covering claude.md, project overview, key concept, repository structure and architecture.
AgentsMesh CLAUDE.md
Claude Code instructions for AgentsMesh/AgentsMesh, covering claude.md, project overview, components, development environment and quick start.
open-forge AGENTS.md
Instructions for zhangqi444/open-forge, covering agents.md, what this project is, working on this repo — the rules, build / test / lint and versioning.
AgentsMesh AGENTS.md
AGENTS.md instructions for AgentsMesh/AgentsMesh: Read CLAUDE.md completely before changing this repository. It is the shared, detailed source for architecture, build, test, and development-environment rules; this file stays short so Codex does not truncate those instructions.
cc-clip CLAUDE.md
Instructions for ShunmeiCho/cc-clip, covering claude.md, what this project does, build & test commands, release process and architecture.
open-forge CLAUDE.md
Instructions for zhangqi444/open-forge, covering claude.md, what is open-forge, architecture — 3 layers, asked in 3 questions, file layout for the 3 layers and a fourth orchestration layer — bundles.