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 commands/pleaseai/claude-code-plugins/add-gemini-extensiongit clone --depth 1 https://github.com/pleaseai/claude-code-pluginsWhat 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 | $0.00036 | $0.01705 |
| Opus 5 | $0.00018 | $0.00852 |
| Sonnet 5 | $0.00007 | $0.00341 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
add-gemini-extension 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new Gemini CLI extension to the marketplace as a Type 4 synced plugin.
Arguments: $ARGUMENTS (format: <extension-name> <github-repo-url>)
Example: /add-gemini-extension firebase https://github.com/pleaseai/firebase-plugin
Step 1 — Parse & Validate Input
Parse $ARGUMENTS to extract:
EXTENSION_NAME: first token (e.g.open-aware)REPO_URL: second token (e.g.https://github.com/qodo-ai/open-aware)
Validate:
- Both tokens are present. If not, stop and show:
Usage: /add-gemini-extension <name> <github-repo-url> REPO_URLmatches patternhttps://github.com/<owner>/<repo>(or[email protected]:<owner>/<repo>). Normalize to HTTPS form.EXTENSION_NAMEcontains only alphanumeric characters, hyphens, and underscores.
Read scripts/meta.ts and verify EXTENSION_NAME is NOT already a key in the extensions object. If it already exists, stop and report: Extension '<name>' already exists in scripts/meta.ts.
Step 2 — Explore Repository
Use the GitHub MCP tool or gh CLI to fetch the gemini-extension.json from the repository:
gh api repos/<owner>/<repo>/contents/gemini-extension.json --jq '.content' | base64 -d
If not found, stop and report:
No gemini-extension.json found in <REPO_URL>.
This repository does not appear to be a Gemini CLI extension.
From gemini-extension.json, extract:
name,version,description(may be absent)contextFileName(optional — triggers SessionStart hook generation)mcpServers(optional — defaults to {} if absent)- Presence of
commands/directory (check via GitHub API)
Check for a commands/ directory (a 404 response means the directory is absent — treat it as an expected optional case, not an error):
gh api repos/<owner>/<repo>/contents/commands 2>/dev/null || echo "[]"
Display a summary of what was found:
Found Gemini extension in <REPO_URL>:
name: <name>
version: <version>
description: <description or "(none)">
contextFileName: <file or "(none)">
mcpServers: <list of server names>
commands/: <yes/no — N .toml files>
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 · 214 lines · 0 tokens per session scan A 7ec122e78072
add-gemini-extension is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 1,705 once invoked, about $0.0002 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 commands, from other repositories
claude-flow-swarm
Coordinate multi-agent swarms for complex tasks.
bootstrap
PACT session-start ritual — identify the session team (platform-provisioned), secretary spawn, paused-state surface, bootstrap marker.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
handoff
Package current state for the next agent.
xdo
Direct development by the Main Agent.