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 skills add angad-kandhari/deliberate --skill architectgit clone --depth 1 https://github.com/angad-kandhari/deliberateWrote 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/skills/angad-kandhari/deliberate/architect)<a href="https://agentmods.dev/skills/angad-kandhari/deliberate/architect"><img src="https://agentmods.dev/badge/skills/angad-kandhari/deliberate/architect/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/skills/angad-kandhari/deliberate/architect"><img src="https://agentmods.dev/badge/skills/angad-kandhari/deliberate/architect.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 | $0.00057 | $0.01563 |
| Opus 5 | $0.00028 | $0.00781 |
| Sonnet 5 | $0.00011 | $0.00313 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
architect 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 9d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
Architectural thinking skill for LLM coding agents. Load this when the task crosses component boundaries, introduces a new service, reshapes a contract, or asks "where should this code live?"
Where deliberate keeps code honest and spec keeps product intent honest, this skill keeps structural decisions honest. Counters premature abstraction, boundary violations, and the silent blurring of component responsibilities.
1. Name the Boundary Before You Cross It
Every non-trivial change touches a boundary. State which one.
Before editing, identify:
- Which component(s) own this code today.
- Which boundary this change sits inside, crosses, or creates.
- What the contract at that boundary is (API, event, schema, function signature).
If the change crosses a boundary that didn't exist before, you're introducing architecture. That's a bigger decision than an implementation. Slow down.
Test: Can I draw a box diagram of the touched components and point to the line my change crosses?
2. Put Code Where It Belongs, Not Where It's Convenient
Where code lives determines who can use it, change it, and break it.
Decide based on:
- Ownership - which team or module is responsible for this behavior?
- Change cadence - does this change with the UI, with the business rule, with the database?
- Dependencies - what does this need to know about? The fewer the better.
- Reuse - is this one-off, or will multiple callers need it?
Common anti-patterns:
- Business logic in the controller/handler layer because it was "just faster."
- Helpers that know about the database and the UI.
- "Utils" dumping grounds that have no coherent responsibility.
- Feature code in shared libraries because one other feature "might need it someday."
Test: If this code needs to change for a business-rule reason, does it live near other business-rule code?
3. Contracts Are Promises - Change Them Carefully
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.
- 9d ago First seen · 166 lines · 57 tokens per session scan A d3a8397866c2
architect is a skill published in the GitHub repository angad-kandhari/deliberate (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,563 once invoked, about $0.0003 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 skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.
x-spec
A system-planning guide that turns a vague idea into a set of linked design documents. It defines goals, modules, interfaces, data, workflows, and ways to check the result.
digest
Generate a structured vibe-learn learning digest of the current coding session from .vibe-learn/session-log.jsonl.
quiz
Check your understanding of the vibe-learn session — recall questions grounded in the session log, with results tracked across sessions in the knowledge ledger.
learn
Explain recent vibe-learn session activity or answer a question about what was built, grounded in .vibe-learn/session-log.jsonl.