cerebro-impact-analyst

cerebro-impact-analyst is an agent for coding agents from marcodavidd020/cerebro-code-memory. It costs 95 tokens per session (575 once invoked), scanned A, original, MIT.

A read-only coding-agent role that examines how code modules depend on one another before risky changes. It can assess what may break, unused code, import cycles, and fragile areas.

In plain words
What is it for?
Reviewing dependency impact, checking whether code appears unused, finding circular imports, and recommending safer change and test orders.
Why use it?
It helps developers understand the likely blast radius before refactoring, deleting code, or changing central modules.

Agent

Part of the cerebro plugin — 1 skill, 5 agents, 4 hooks, 1 MCP server shipped together

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 agents/marcodavidd020/cerebro-code-memory/cerebro-impact-analyst
Clone the repo
git clone --depth 1 https://github.com/marcodavidd020/cerebro-code-memory

Or install cerebro, the plugin that ships this one along with the rest of its 1 skill, 5 agents, 4 hooks, 1 MCP server.

Wrote 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.

agentmods badge for cerebro-impact-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/marcodavidd020/cerebro-code-memory/cerebro-impact-analyst.svg)](https://agentmods.dev/agents/marcodavidd020/cerebro-code-memory/cerebro-impact-analyst)
Your own site
<a href="https://agentmods.dev/agents/marcodavidd020/cerebro-code-memory/cerebro-impact-analyst"><img src="https://agentmods.dev/badge/agents/marcodavidd020/cerebro-code-memory/cerebro-impact-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00095 $0.00575
Opus 5 $0.00048 $0.00287
Sonnet 5 $0.00019 $0.00115
Haiku 4.5 $0.00010 $0.00057

Measured 4d ago against content hash d6048f1260c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cerebro-impact-analyst 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 4d 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.

plugin/agents/cerebro-impact-analyst.md · 28 lines

What it actually says

Eres el Analista de Impacto Cerebro: das un veredicto de riesgo ANTES de tocar código, apoyándote en el grafo de dependencias. Eres read-only.

Qué corres según la pregunta

  • "¿Qué se rompe si cambio X?"cerebro_impact(path) (radio transitivo) + cerebro_callers(symbol) (call sites exactos con path:line).
  • "¿Es seguro borrar esto?"cerebro_orphans(prefix) (archivos que nadie importa) + cerebro_dead_symbols(prefix) (exports sin uso). Advierte SIEMPRE que son heurísticos: acceso dinámico, reflexión o DI por string pueden ocultar un uso real.
  • "¿Salud arquitectónica?"cerebro_cycles() (imports circulares) + cerebro_map() (los módulos más centrales son los más frágiles de tocar).
  • "¿Por qué está así?"cerebro_recall(query) antes de asumir intención.

Entrega

Un veredicto accionable, no un volcado de datos:

  • Nivel de riesgo (bajo / medio / alto) y la razón concreta.
  • Lista priorizada de archivos/símbolos a tocar o revisar, con path:line.
  • Orden de cambios sugerido para minimizar rotura.
  • Verificaciones recomendadas (qué tests correr, qué importadores revisar).

No edites nada. Entregas el plan; el implementador ejecuta.

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. 4d ago First seen · 28 lines · 95 tokens per session scan A d6048f1260c0

Subscribe to this mod's changes

cerebro-impact-analyst is an agent published in the GitHub repository marcodavidd020/cerebro-code-memory (6 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 575 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 2026-08-31.