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/ashlrai/ashlr-stack/applygit clone --depth 1 https://github.com/ashlrai/ashlr-stackWhat 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 | $0.00027 | $0.00372 |
| Opus 5 | $0.00014 | $0.00186 |
| Sonnet 5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
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.
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_addfor 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.tomland 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:doctorto 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.
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 · 31 lines · 27 tokens per session scan A 3b5da420fb04
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.
Other commands, from other repositories
pipeline
Run the full delivery pipeline (planner → red-team → coder → smoke-tester → reviewer) against a GitHub issue. Bridges Claude Code's missing auto-handoff button by invoking each subagent in sequence via the Agent tool, validating typed HANDOFF blocks, breaking on repeat failures, and logging every stage to…
10x-plan
Create detailed implementation plans with thorough research and iteration.
10x-research
Research codebase comprehensively using parallel sub-agents.
shadcn-ui-plan
Prompt do wygenerowania wysokopoziomowej architektury UI w .ai/ui-plan.md.
shadcn-view-plan
Prompt do przygotowania szczegółowego planu implementacji widoku (.ai/{view}-view-implementation-plan.md).
10x-implement
Implement technical plans from thoughts/shared/plans with verification.