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/osouthgate/agent-plus/agents-mdgit clone --depth 1 https://github.com/osouthgate/agent-plusWhat 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 | $0.02436 | $0.02436 |
| Opus 5 | $0.01218 | $0.01218 |
| Sonnet 5 | $0.00487 | $0.00487 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade D, and why
agent-plus AGENTS.md scanned grade D with 3 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://github.com/osouthgate/agent-plus/releases/latest/download/install.sh | sh Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Missing-config errors point to both `.env` and `~/.claude/settings.json`** so the user knows where to put the value. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://github.com/osouthgate/agent-plus/releases/latest/download/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Durable instructions for any coding agent (Claude Code, Codex, Cursor, Aider) working in this repo. If you're Claude Code, treat this as memory.
For context on what this repo is and why it exists, see README.md. This file is operational rules only.
Plugins in this repo
| Plugin | Killer command |
|---|---|
agent-plus-meta |
init, envcheck, refresh, marketplace install|list|update|remove|search|prefer |
repo-analyze |
repo-analyze [--output] [--shape-depth] [--pretty] |
diff-summary |
diff-summary [--staged | --base BRANCH | --range A..B] [--public-api-only] [--risk MIN] |
skill-feedback |
log <skill> --rating --outcome [--friction], report, submit |
skill-plus |
scan, propose, scaffold <name> --from-candidate <id>, inquire <tool> [--audit], list, feedback, promote <name> |
Service wrappers (github-remote, vercel-remote, supabase-remote, railway-ops, linear-remote, openrouter-remote, langfuse-remote, hermes-remote, coolify-remote, hcloud-remote) moved to osouthgate/agent-plus-skills.
Installing agent-plus
If asked to install agent-plus for the user, run:
macOS / Linux:
curl -fsSL https://github.com/osouthgate/agent-plus/releases/latest/download/install.sh | sh
Windows (PowerShell):
powershell -c "irm https://github.com/osouthgate/agent-plus/releases/latest/download/install.ps1 | iex"
Then register the plugins with Claude Code so they're callable as tools:
claude plugin marketplace add osouthgate/agent-plus
for p in agent-plus-meta repo-analyze diff-summary skill-feedback skill-plus; do
claude plugin install $p@agent-plus
done
Then reload: /reload-plugins in the current session, or open a new one.
The install script chains into agent-plus-meta init automatically — the workspace wizard runs as part of install. If the user skipped that, they can run agent-plus-meta init manually.
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 · 156 lines · 2,436 tokens per session scan D 04b61c02006f
agent-plus AGENTS.md is an instructions file published in the GitHub repository osouthgate/agent-plus (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,436 tokens to every session, about $0.0122 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mirage CLAUDE.md
Claude Code instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
kinocut CLAUDE.md
Claude Code instructions for KyaniteLabs/kinocut, covering claude.md instructions for kyanitelabs/kinocut and empower orchestrator law.
trustabl GEMINI.md
Instructions for trustabl/trustabl, a project described as: Fix agent reliability issues across Claude, OpenAI, Google ADK, MCP, LangChain, CrewAI, AutoGen, Pydantic AI, and Vercel AI.
hermes-agent-harness-plus CLAUDE.md
Instructions for phenomenoner/hermes-agent-harness-plus, covering claude.md, what this repo is, before touching readme, docs/, or the website, commands and deployment.
skillpack copilot-instructions.md
Instructions for nordicnode/skillpack, covering skillpack, when to use, when not to use, installation and invocation.
compounded CLAUDE.md
Instructions for ankitkr3/compounded, covering claude.md (compounded repository), what this repo is, conventions, how the lifecycle works and what you can change.