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/vaibhavsing/openghost/agents-mdgit clone --depth 1 https://github.com/VAIBHAVSING/openghostWhat 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 | $0.01701 | $0.01701 |
| Opus 5 | $0.00851 | $0.00851 |
| Sonnet 5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
openghost 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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project context for coding agents working on OpenGhost.
What This Repo Is
OpenGhost is an original standalone Agent Skill for authorized web application and server integrity penetration testing. The repo packages skill instructions, reference methodology, evidence/reporting helpers, and a Docker-backed launcher that keeps security tooling out of the host environment.
The central design constraint is simple: agents provide reasoning and workflow control, while OpenGhost provides the sandboxed execution layer and structured engagement state.
Product Boundary
- This repository owns the OpenGhost skill package and sandbox launcher.
- Security tools must be executed through
openghost, not directly on the host. - External research/reference directories are not runtime dependencies and should not be cited as OpenGhost source material.
- Generated engagement data belongs under
.openghost/and should normally stay uncommitted.
Agent Skill Structure
OpenGhost follows the standard Agent Skill layout:
skills/openghost-skill/SKILL.mdis the published skill entrypoint and operator workflow.- Keep
SKILL.mdfocused and use progressive disclosure: short entrypoint instructions first, deeper details in references. skills/openghost-skill/references/contains deeper guidance that agents should load only when relevant.skills/openghost-skill/scripts/contains deterministic helpers and launcher implementation.skills/openghost-skill/assets/contains templates and reusable output files.- Do not duplicate large methodology content across files; link to the canonical reference instead.
Main Source Paths
skills/openghost-skill/SKILL.md- published skill entrypoint and operator workflow.skills/openghost-skill/references/- deeper guidance for modules, reporting, tooling, auth, and workflow.skills/openghost-skill/references/modules/- assessment modules such as surface mapping, session auth, access control, injection, APIs, browser policy, HTTP edge, business logic, and server integrity.skills/openghost-skill/scripts/openghost.sh- canonical CLI and Docker sandbox implementation.skills/openghost-skill/scripts/verify-toolchain.sh- runtime toolchain verification.skills/openghost-skill/scripts/select-modules.py- module selection helper.skills/openghost-skill/assets/- templates for scope, auth, findings, and reports.skills/openghost-skill/agents/- compatibility notes for other coding agents.
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.
- 2d ago First seen · 177 lines · 1,701 tokens per session scan A afa6738ed8cd
openghost AGENTS.md is an instructions file published in the GitHub repository VAIBHAVSING/openghost (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,701 tokens to every session, about $0.0085 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.
Other instructions, from other repositories
xlsx-for-ai CLAUDE.md
Instructions for senoff/xlsx-for-ai, covering xlsx-for-ai — agent loading guide, always-load, load on relevance, review gate (mandatory unless explicitly skipped) and repo posture.
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
rails-ai-context AGENTS.md
Instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
llm-ide-rules typescript.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering typescript and dates & times.
agenttop CLAUDE.md
Instructions for vicarious11/agenttop, covering agenttop — ai usage dashboard & optimizer, project overview, architecture, layers and key directories.