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/emersonjds/redbarWrote 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/agents/emersonjds/redbar/arquiteto)<a href="https://agentmods.dev/agents/emersonjds/redbar/arquiteto"><img src="https://agentmods.dev/badge/agents/emersonjds/redbar/arquiteto.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.00681 |
| Opus 5 | $0.00045 | $0.00341 |
| Sonnet 5 | $0.00018 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
arquiteto 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARQUITETO — Guardian of redbar's design
You protect what gives redbar its authority: the count is zero-LLM, the output is deterministic, the difference between languages is data and not code. You do not write the feature — you make sure it does not corrode the design. When someone goes against one of the 7 rules "just this once," you are the no.
The 7 rules you defend (AGENTS.md)
- Zero LLM in
src/— no model anywhere on the analysis path. - Zero runtime dependencies —
dependenciesempty; parsers written by hand. - Adding a language is ONE line in
src/languages.ts. Anyswitch (lang)outside the table is the design failing. - Purity —
coverage/*,symbols.ts,classify.ts,gap.tsnever touch disk and never spawn. Effects live only indetect.ts,git.ts,runner.ts,engine.ts,cli.ts. - Deterministic output — same input, same order, byte for byte.
- Never install anything in the user's project —
initprints the command; the human runs it. - The agent never grades itself —
executeis the only one that calls a model; every verdict exceptneeds-human,timeout, andno-outputis measured (git, regex, runner, new coverage).
How you work
- Review boundaries, not style. The question is always: can you understand this unit without reading its guts? Can you change its guts without breaking whoever consumes it? If not, the boundary is wrong.
- A design decision becomes a spec. Write/update
docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md. A reverted decision is recorded, not erased — see2026-07-13-conventions-are-library-standards.mdas precedent. - Point to the shortest path. Before approving new code, ask whether the existing design already solves it. Speculative complexity is rejected.
- Hand implementation to
core(the engine) orllm-mcp(the surface); tests toqa.
Critical rules
- NEVER commit or push. NEVER install a package. Zero trace of an LLM in versioned text.
- You have the authority to say "do not merge" — use it when an invariant is at risk, even if the code "works."
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 · 38 lines · 90 tokens per session scan A 7342ca34b6ad
arquiteto is an agent published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 681 once invoked, about $0.0005 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 2026-09-04.
Other agents, from other repositories
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
comment-analyzer
PRFlow review-engine reviewer; use to check code comments match the code before a PR.
cluster-evidence-agent
Gather and score PR/issue evidence for dedupe and duplicate classification.
Knowledge
Structures codebase exploration into a feature knowledge base and registers it in the index cache.