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/caliber-ai-org/ai-setup/adding-a-commandnpx skills add caliber-ai-org/ai-setup --skill adding-a-commandgit clone --depth 1 https://github.com/caliber-ai-org/ai-setupWhat 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 | $0.00076 | $0.01851 |
| Opus 5 | $0.00038 | $0.00925 |
| Sonnet 5 | $0.00015 | $0.00370 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
adding-a-command 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Command
Critical
- Export pattern: Command must export a named async function:
export async function myCommand(options?: OptionType). Never use default exports. - Registration in cli.ts: Every command must be imported and registered with
.command()chain insrc/cli.ts, wrapped withtracked()for telemetry. - Error signaling: Use
throw new Error('__exit__')to exit gracefully without printing the error message. Use chalk for user-facing messages. - Options typing: Commands receiving options must define a TypeScript interface for those options. Pass options as a destructured object parameter.
Instructions
-
Create the command file at
src/commands/{commandName}.tswith named async export.- Signature:
export async function {commandName}Command(options?: { optionName?: optionType }) { ... } - Import only what you need (avoid kitchen-sink imports).
- Return void (handle all output via console.log or chalk).
- Verify the file follows the naming convention: camelCase function + "Command" suffix.
- Signature:
-
Handle errors consistently: Wrap error-prone operations in try/catch. Distinguish between user errors and system errors:
- User error (bad input):
console.error(chalk.red('message')); throw new Error('__exit__'); - System error (missing dependency):
throw new Error('Detailed error message');— this will print and exit with code 1. - Parse-like errors: Use ora spinner with
.fail()before throwing. - This step prevents double error printing in bin.ts.
- User error (bad input):
-
Import and register in src/cli.ts in the correct location:
- Add import at the top:
import { {commandName}Command } from './commands/{commandName}.js'; - Register the command in the appropriate section (main commands, or nested under a group like
sources). - For main commands:
.command('{kebab-name}').description('...').option(...).action(tracked('{kebab-name}', {commandName}Command)) - For subcommands (like
sources add):sources.command('add').description(...).action(tracked('sources:add', sourcesAddCommand)) - Key: Wrap handler with
tracked('{command-name}', handler)for automatic telemetry. - Verify the command name in tracked() uses kebab-case for main commands and colon-separated for subcommands.
- Add import at the top:
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 · 181 lines · 76 tokens per session scan A 73e93413cd36
adding-a-command is a skill published in the GitHub repository caliber-ai-org/ai-setup (1,259 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,851 once invoked, about $0.0004 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 skills, from other repositories
bridge
Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…
prompt-optimization
Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.
fable-method
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no…
fable-domain
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain ", "make a skill for ", "add a domain to the fable method", or "give a lesser…
fable-judge
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model…
fable-loop
End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable…