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.
git clone --depth 1 https://github.com/ashlrai/ashlr-stackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ashlrai/ashlr-stack/recommend)<a href="https://agentmods.dev/commands/ashlrai/ashlr-stack/recommend"><img src="https://agentmods.dev/badge/commands/ashlrai/ashlr-stack/recommend/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ashlrai/ashlr-stack/recommend"><img src="https://agentmods.dev/badge/commands/ashlrai/ashlr-stack/recommend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00366 |
| Opus 5.5 | $0.00009 | $0.00146 |
| Sonnet 5.5 | $0.00005 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
recommend 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_recommend via the ashlr-stack MCP server with the user's query. Pass save: true so the recipe is persisted, and k: 6 so the top 6 hits come back.
Invocation:
stack_recommend { query: "<user's input>", save: true, k: 6 }
Then render the hits as a short bulleted list, one line per provider:
• <displayName> <category> — <rationale-or-blurb>
After the list, show the saved recipe id on its own line (e.g. Recipe: rec_xxx).
Suggest the next step verbatim:
Review the saved recipe, then run
/stack:apply <recipe-id>for the provider setup you authorize; inspect its partial results.
If the tool is unavailable, explain the required setup: inside Claude Code use /plugin marketplace add ashlrai/ashlr-stack, then /plugin install stack@ashlr. The plugin entrypoint prefers ashlr-stack-mcp on PATH and otherwise needs the monorepo source plus Bun. The server also needs the Stack CLI on PATH and the intended project as its working directory. Installing the CLI alone does not install or commission the server. Recorded public CLI/MCP 0.1.1 needs Bun 1.2+; reviewed source 0.2.1 is a separate candidate, not proof of publication. Check the actual client tools after setup.
If the user gave no query, ask them one clarifying question about the goal (e.g. "what are you building?") before calling the tool.
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 Changed 2897d8f35f75
- 1mo ago First seen · 28 lines · 23 tokens per session scan A 9e1b2d26e867
recommend is a command published in the GitHub repository ashlrai/ashlr-stack (2 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 366 once invoked, about $0.0001 per session on Opus 5.5. 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
setup
Set up Duel Agents routing with your Duel API key.
generate-docs
Generate comprehensive technical documentation across infrastructure, backend, and frontend domains using a 7-stage pipeline.
assert
Validate implementation completeness, correctness, and compliance before testing phase through static analysis and requirements verification.
commit
Analyze changes and create atomic, conventional commits with intelligent message generation, version management, changelog updates, and quality insights.
gather-knowledge
Analyze codebase, dependencies, patterns, and constraints to build comprehensive technical context for planning or implementation.
refine-task
Clarify task requirements, acceptance criteria, and implementation details before planning phase.