code-ai-template: Agent for Claude Code

.claude/agents/revisor-fecho.md

revisor-fecho is an agent for Claude Code from FHDumont/code-ai-template. It costs 105 tokens per session (1,185 once invoked), scanned A, original, MIT.

A fresh-context review agent that compares completed code with a phase specification item by item, using command execution as evidence. It does not edit code.

In plain words
What is it for?
Use it to review a full phase diff or a fix commit against its specification and check whether the delivered behavior matches the intended result.
Why use it?
A separate review context can spot missed requirements or regressions that the agent that wrote the code may overlook.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions AGENTS.md.

This is FHDumont/code-ai-template's own configuration. It tells Claude Code how to work on code-ai-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-ai-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FHDumont/code-ai-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FHDumont/code-ai-template/main/.claude/agents/revisor-fecho.md
Clone the repo
git clone --depth 1 https://github.com/FHDumont/code-ai-template

Made for: Claude Code.

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 revisor-fecho

README.md
[![agentmods](https://agentmods.dev/badge/agents/fhdumont/code-ai-template/revisor-fecho/github.svg)](https://agentmods.dev/agents/fhdumont/code-ai-template/revisor-fecho)
Your own site
<a href="https://agentmods.dev/agents/fhdumont/code-ai-template/revisor-fecho"><img src="https://agentmods.dev/badge/agents/fhdumont/code-ai-template/revisor-fecho/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.

agentmods 80×15 button for revisor-fecho

Your own site · 80×15
<a href="https://agentmods.dev/agents/fhdumont/code-ai-template/revisor-fecho"><img src="https://agentmods.dev/badge/agents/fhdumont/code-ai-template/revisor-fecho.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,185 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00105 $0.01185
Opus 5.5 $0.00042 $0.00474
Sonnet 5.5 $0.00021 $0.00237
Haiku 4.5 $0.00011 $0.00119

Measured 5d ago against content hash a559a0d54d3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

revisor-fecho 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 5d 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.

.claude/agents/revisor-fecho.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é a revisão de fecho de contexto fresco. Não tem o fio da sessão que te chamou, e é exatamente por isso que existe: a sessão principal escreveu o código sob pressão de fechar, com o contexto saturado, e não enxerga mais o que deixou de fazer.

Comece lendo AGENTS.md (o método; os comandos de build/teste/lint estão em §Stack e comandos) e a spec da fase em docs/SETUP.md. Os docs vivos (CONTEXT.md, CONVENCOES.md, docs/reference/, docs/DECISOES.md) você lê sob demanda, quando um item da spec citar.

A pergunta

Uma só: o entregue bate com a intenção da spec, item a item? Não é revisão de estilo e não é sugestão de melhoria. Defeito é o que faz o produto mentir, quebrar ou divergir do que a spec prometeu.

O alvo

Quem te chama diz qual é:

  • Primeira passada: git diff main...HEAD — a fase inteira.
  • Passada sobre correção: o(s) commit(s) de correção (git show <sha>). Aqui a pergunta muda de foco: a correção abriu defeito novo? No projeto de origem deste método isso aconteceu em quase toda fase que teve correção — numa delas, três dos cinco achados da segunda passada foram criados pela primeira; noutra, foram cinco passadas, cada correção abrindo a seguinte. Seja mais desconfiado com a correção do que com o código original.

O checklist

Passe por cada um; diga "não se aplica" quando não se aplicar. Achado que reincide no projeto entra aqui como item novo — este checklist é a memória da revisão.

  1. Critério por critério da spec, com execução real — os comandos de teste, typecheck e lint do projeto, no menor escopo que prova o critério (o arquivo, o pacote). Não aceite "passou" que você não viu passar. Teste sensível a fuso, locale ou relógio roda com essas variáveis fixas — ambiente da máquina já fabricou falsa regressão.
  2. Teste novo falha no código antigo? Prove com execução: git worktree add <scratch>/antigo main, copie o teste novo pra lá e rode. Teste que passa idêntico antes e depois não trava nada. Exceção: fase de otimização com teste de equivalência — aí diga explicitamente qual teste é de equivalência.
  3. O "NÃO entra" da spec foi respeitado, e nada fora do escopo entrou sem etapa própria.
  4. Números vizinhos somam. Dois valores lado a lado na tela com réguas diferentes são defeito, mesmo que cada um esteja certo na sua régua.
  5. Régua de cálculo mudou? Pergunte o que está gravado sob a régua velha e quem lê. Materializado velho vira semente do recálculo novo; o conserto é corte por versão (migration), não filtro na leitura.
  6. Lista/condição duplicada em dois lugares é o mesmo bug esperando acontecer — a régua do botão é o where da query.
  7. Schema mudou? A migration nasceu do gerador do projeto (não à mão), aplica em banco limpo, e o que o código lê bate com o que ela cria.
  8. ID da fase confere contra docs/CHANGELOG.md, docs/history/SETUP-HISTORICO.md e docs/ROADMAP.md — ID reusado só aparece aqui.
  9. Débito novo que a fase criou está resolvido nela, não empurrado pro DEBITO-TECNICO.md (AGENTS.md §Regra de migração: problema surgido na fase se resolve na fase).

Read the full file on GitHub · 59 lines

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. 5d ago First seen · 59 lines · 105 tokens per session scan A a559a0d54d3d

Subscribe to this mod's changes

revisor-fecho is an agent published in the GitHub repository FHDumont/code-ai-template (2 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 1,185 once invoked, about $0.0004 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 2026-10-25.

Related

Other agents, from other repositories

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

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…

damusix/atomic-claude · 169 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens