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/agirails/claude-plugin/initgit clone --depth 1 https://github.com/agirails/claude-pluginWhat 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 | $0.00032 | $0.01068 |
| Opus 5 | $0.00016 | $0.00534 |
| Sonnet 5 | $0.00006 | $0.00214 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
init scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sLO https://www.agirails.app/protocol/AGIRAILS.md How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agirails:init
Set up AGIRAILS agent payments in the current project.
This command does NOT reimplement onboarding. The canonical, always-current onboarding flow lives in the protocol file at
https://www.agirails.app/protocol/AGIRAILS.md. This command's only job is to fetch that file and follow it exactly. Anything you reimplement here will drift out of date the moment the protocol moves — so don't.
Do this, in order
1. Fetch the canonical protocol file
curl -sLO https://www.agirails.app/protocol/AGIRAILS.md
(Or WebFetch the same URL.) This file is ~50 KB of YAML + Markdown. It is the
authoritative spec AND the onboarding script — it contains an onboarding: block
with the exact questions to ask, the order to ask them in, and the commands to run.
2. Read it and follow its onboarding section literally
Read the file you just downloaded. Find the onboarding: block in the YAML
frontmatter. It defines:
- the questions to ask the user (name, intent, services, price, budget, …),
including which are conditional on
intent(a pay-only buyer is not asked for a selling price; an earn-only provider is not asked what it wants to buy); - the defaults to apply WITHOUT asking (network → testnet, wallet → generate);
- the setup steps to run.
Ask the questions with AskUserQuestion. Apply the no-ask defaults silently. Then
run the setup the file describes. As of this writing the happy path is a single
command:
npx @agirails/sdk@latest init --mode testnet --intent <pay|earn|both> --test
— which generates an encrypted keystore, auto-mints 1,000 test USDC (gasless), links/publishes the agent, then drives a real on-chain transaction against the network's default counterparty (Sentinel) all the way to SETTLED, ending with a public receipt URL and a framed receipt. But do not hard-code that command from this doc — read the version in the freshly-downloaded AGIRAILS.md and run what IT says, because the flags and steps evolve.
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.
- yesterday First seen · 100 lines · 32 tokens per session scan A f21399ada38a
init is a command published in the GitHub repository agirails/claude-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,068 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.