You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The audit checks Claude Code, Codex CLI, Gemini CLI, and `caam` without printing token values or auth file contents. It reports CLI presence, version availability, parseable auth/config files, CAAM default profile consistency, and stale CAAM defaults that point at missing profiles.
2389
+
The audit checks Claude Code, Codex CLI, Antigravity CLI, and `caam` without printing token values or auth file contents. It reports CLI presence, version availability, parseable auth/config files, CAAM default profile consistency, and stale CAAM defaults that point at missing profiles.
2390
2390
2391
2391
Useful options:
2392
2392
@@ -3004,7 +3004,7 @@ Currently, ACFS installs the full suite. Future versions will support:
3004
3004
3005
3005
### The Problem: The Agentic Coding Barrier
3006
3006
3007
-
The rise of AI coding agents (Claude Code, Codex CLI, Gemini CLI) has created a new paradigm in software development. These agents can write code, debug issues, and even architect solutions—but only if they have the right environment.
3007
+
The rise of AI coding agents (Claude Code, Codex CLI, Antigravity CLI) has created a new paradigm in software development. These agents can write code, debug issues, and even architect solutions—but only if they have the right environment.
3008
3008
3009
3009
**The barrier isn't the agents themselves.** It's the **hours of setup** required to create an environment where agents can actually be productive:
3010
3010
@@ -3074,7 +3074,7 @@ ACFS isn't just a collection of tools—it's a **carefully curated system** wher
Copy file name to clipboardExpand all lines: apps/web/app/complete-guide/page.tsx
+4-4Lines changed: 4 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -1244,7 +1244,7 @@ And you can't do this sort of thing using regex or a script, you MUST manually r
1244
1244
<SubSectiontitle="Vendor Lock-In: Avoid It">
1245
1245
<BlockQuote>PSA: you should avoid vendor lock-in for agent coding primitives like task management (e.g., beads) and agent communication (e.g., MCP Agent Mail) so you can use all the agents together, which is more powerful anyway. They want you in a walled garden, but it's 100% unnecessary.</BlockQuote>
1246
1246
1247
-
<P>Beads, Agent Mail, and bv are all CLI tools that work identically regardless of which agent invokes them. A Claude Code agent and a Codex agent and a Gemini agent can all call <code>br ready --json</code> and get the same task list. The practical test: could you swap out every Claude Code agent for Codex or Gemini without changing your AGENTS.md, beads, Agent Mail setup, or workflow? If yes, you're vendor-neutral.</P>
1247
+
<P>Beads, Agent Mail, and bv are all CLI tools that work identically regardless of which agent invokes them. A Claude Code agent, a Codex agent, and an Antigravity agent can all call <code>br ready --json</code> and get the same task list. The practical test: could you swap out every Claude Code agent for Codex or Antigravity without changing your AGENTS.md, beads, Agent Mail setup, or workflow? If yes, you're vendor-neutral.</P>
1248
1248
</SubSection>
1249
1249
1250
1250
<SubSectiontitle="Validation Gates">
@@ -1268,14 +1268,14 @@ And you can't do this sort of thing using regex or a script, you MUST manually r
1268
1268
1269
1269
<CodeBlocklanguage="bash"code={`alias cc='NODE_OPTIONS="--max-old-space-size=32768" claude --dangerously-skip-permissions'
1270
1270
alias cod='codex --dangerously-bypass-approvals-and-sandbox'
alias gmi='gemini --yolo' # legacy: Gemini CLI retired 2026-06-18`}/>
1271
+
alias agy='agy-locked'
1272
+
alias gmi='agy-locked' # legacy shortcut now launches agy`}/>
1273
1273
1274
1274
<P>These are configured automatically by the installer. DCG provides the safety net that makes this viable.</P>
1275
1275
</SubSection>
1276
1276
1277
1277
<SubSectiontitle="Cost">
1278
-
<P>~$500/month for Claude Max and GPT Pro subscriptions (at minimum), plus ~$50/month for a cloud server (OVH, Contabo). Multiple Max accounts may be needed for large swarms; CAAM enables instant switching when hitting rate limits. At scale, token usage for a single intensive session can reach ~20M input tokens, ~3.5M output tokens, ~2.6M reasoning tokens, and ~1.15 billion cached token reads. At full scale: 22 Claude Max accounts, 22 GPT Pro accounts, and 7 Gemini Ultra accounts.</P>
1278
+
<P>~$500/month for Claude Max and GPT Pro subscriptions (at minimum), plus ~$50/month for a cloud server (OVH, Contabo). Multiple Max accounts may be needed for large swarms; CAAM enables instant switching when hitting rate limits. At scale, token usage for a single intensive session can reach ~20M input tokens, ~3.5M output tokens, ~2.6M reasoning tokens, and ~1.15 billion cached token reads. At full scale: 22 Claude Max accounts, 22 GPT Pro accounts, and 7 Google/Antigravity-capable accounts.</P>
"Transform a fresh cloud server into a fully-configured agentic coding environment in ~30 minutes. Claude Code, OpenAI Codex, Google Gemini: all pre-configured with 30+ modern developer tools. Free & open-source.",
31
+
"Transform a fresh cloud server into a fully-configured agentic coding environment in ~30 minutes. Claude Code, OpenAI Codex, Google Antigravity: all pre-configured with 30+ modern developer tools. Free & open-source.",
0 commit comments