apply

A command for applying a saved service setup recipe to a project. It adds the listed providers and can record their configuration, secrets, and webhook placeholders.

In plain words
What is it for?
Use it with a recipe ID to add providers, update .stack.toml and MCP entries, request protected secret envelopes, and optionally skip credential wiring with --no-wire.
Why use it?
It saves time when several services must be configured together and makes it possible to preview the provider list without wiring real credentials.

Command

Install

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.

agentmods
npx agentmods add commands/ashlrai/ashlr-stack/apply
Clone the repo
git clone --depth 1 https://github.com/ashlrai/ashlr-stack
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00372
Opus 5 $0.00014 $0.00186
Sonnet 5 $0.00005 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured yesterday against content hash 3b5da420fb04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apply 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 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.

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.

packages/plugin/commands/apply.md · 31 lines

What it actually says

Call stack_apply via the ashlr-stack MCP server with the recipe id the user provided.

Invocation:

stack_apply { recipe_id: "<user's input>", no_wire: false }

What stack_apply does:

  • Runs stack_add for each provider in the recipe (creates resources where the provider supports it, otherwise stubs the entry).
  • Requests rotating envelopes from Phantom for every secret slot so keys are encrypted at rest and can be rotated without code changes.
  • Writes webhook stubs for providers that emit events (Stripe, Clerk, GitHub, Linear, Resend, etc.) so the app can wire them later.
  • Updates .stack.toml and the MCP entries in one pass.

If the user appends --no-wire (e.g. /stack:apply rec_xxx --no-wire), call with no_wire: true instead. That skips the Phantom envelopes + webhook stubs and only records the providers in .stack.toml — useful when the user wants to inspect what would happen before wiring real credentials.

After the call succeeds, summarize:

  • Which providers were added
  • Any providers that were skipped and why (already present, missing API credentials, etc.)
  • The path of the updated .stack.toml

Then suggest the next step verbatim:

Run /stack:doctor to verify every service is reachable and credentials are valid.

If stack_apply fails because Phantom is not installed, surface the install hint: brew install ashlrai/phantom/phantom. If the recipe id is not found, suggest /stack:recommend <query> to create a new one.

Changes

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.

  1. yesterday First seen · 31 lines · 27 tokens per session scan A 3b5da420fb04

Subscribe to this mod's changes

apply is a command published in the GitHub repository ashlrai/ashlr-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 372 once invoked, about $0.0001 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.