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 skills/osouthgate/agent-plus/agent-plus-metanpx skills add osouthgate/agent-plus --skill agent-plus-metagit clone --depth 1 https://github.com/osouthgate/agent-plusWrote 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/skills/osouthgate/agent-plus/agent-plus-meta)<a href="https://agentmods.dev/skills/osouthgate/agent-plus/agent-plus-meta"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus/agent-plus-meta.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 | $0.00103 | $0.03565 |
| Opus 5 | $0.00051 | $0.01783 |
| Sonnet 5 | $0.00021 | $0.00713 |
| Haiku 4.5 | $0.00010 | $0.00357 |
Grade A, and why
agent-plus-meta 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-plus-meta
The meta plugin. Eight+ subcommands across init, envcheck, refresh, list, extensions, marketplace, doctor. JSON output only. Use at session start to give the agent day-one context — installed plugin set, env-var readiness, resolved project IDs — without grep-mining the project for every fact.
The binary lives at ${CLAUDE_SKILL_DIR}/../../bin/agent-plus-meta; the plugin loader auto-adds bin/ to PATH, so call it as agent-plus-meta.
When to reach for this
At session start, run agent-plus-meta envcheck once. It tells you which plugins are configured in this workspace without you having to read every .env and README. If the user asks for a service you can see in set: use the corresponding plugin; otherwise, surface what's missing.
After running agent-plus-meta refresh once per session, treat services.json as the single source of truth for project IDs and service handles. Don't re-resolve.
# Session-start bootstrap (run once)
agent-plus-meta init # idempotent; creates .agent-plus/ if missing
agent-plus-meta envcheck # which plugin env vars are set?
agent-plus-meta refresh # resolves github + vercel identity into services.json
# "Is X configured?" questions
agent-plus-meta envcheck --pretty | jq '.plugins["hermes-remote"].ready'
Always surface nextSteps
After ANY agent-plus-meta call, read nextSteps and surface the next command to the user -- every time, not just on the first call. Every subcommand's JSON envelope carries a nextSteps array (1-2 entries, most-important first). Each entry is a literal "<runnable command> -- <why>" string; the command always starts with agent-plus-meta, repo-analyze, skill-plus, skill-feedback, diff-summary, claude, or git -- it is copy-paste runnable, never a natural-language question re-phrased back at yourself. This chain (roughly: install -> init -> envcheck -> skill-plus scan for a returning user with prior session history, or -> repo-analyze for a brand-new one -- with an equivalent mapping for doctor/refresh/list/upgrade/upgrade-check/uninstall/marketplace/extensions) is the product's first-win path; dropping it silently anywhere in the chain breaks onboarding for the rest of the session.
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.
- 4d ago First seen · 194 lines · 103 tokens per session scan A 581d43e86c27
agent-plus-meta is a skill published in the GitHub repository osouthgate/agent-plus (4 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 3,565 once invoked, about $0.0005 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 skills, from other repositories
notify-user
Telegram comms playbook for Antigravity — when and how to reply, ack long work, present choices, and delegate to other agents. Use whenever you're paired to a Telegram chat via the telegram-agy MCP server and need to talk back to the user. The chat is your only signal channel — terminal output never reaches the user.
rag-your-code
Index and search the current codebase with local, explainable RAG records.
slack-cli
Complete Slack Web API CLI — 201 methods across 29 command groups. Every public endpoint. Agent-friendly JSON output. Auto-generated from the official OpenAPI spec + @slack/web-api SDK. Use when: sending messages, reading channels, adding reactions, managing files, searching, pins, bookmarks, reminders, user groups…
slack-messages
Send Slack messages to channels or users via the elnora-slack CLI. Resolves channel/user IDs from the cached workspace reference, formats messages, handles threads and DMs, and enforces a draft-and-approve gate before anything is sent. TRIGGERS: "send slack", "slack message", "post on slack", "message on slack", "tell…
compounded-author
Use this skill when you have just completed a non-trivial task (more than 3 tool calls, novel approach, recovery from a dead end) and are considering whether to save the procedure as a reusable skill via compounded; OR in RULE MODE when the user corrected your approach and the correction encodes a generalizable…
compounded-verifier
Use this skill ONLY when invoked as the skill-verifier subagent by compounded's Stop hook. This is the rubric for deciding whether a proposed skill should graduate to .verified or move to .rejected/ based on its replayability against a just-completed task. Do not invoke this skill in normal sessions.