rule-blame

rule-blame is a skill for Claude Code, Codex from Renzo-Tognella/DecisionsSearch. It costs 91 tokens per session (1,446 once invoked), scanned A, original, MIT.

A history report for a business rule, meaning a statement about how the product or organisation should behave. It reconstructs the rule’s versions, the pull requests that changed it, and the recorded reason for each change.

In plain words
What is it for?
Auditing or investigating the evolution of a business rule and identifying the PRs and evidence behind its changes.
Why use it?
It shows how a rule reached its current form instead of presenting only the latest wording.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Auditing or investigating the evolution of a business rule and identifying the PRs and evidence behind its changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/renzo-tognella/decisionssearch/rule-blame
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.

Any agent
npx skills add Renzo-Tognella/DecisionsSearch --skill rule-blame
Clone the repo
git clone --depth 1 https://github.com/Renzo-Tognella/DecisionsSearch

Made for: Claude Code, Codex.

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 rule-blame

README.md
[![agentmods](https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/rule-blame/github.svg)](https://agentmods.dev/skills/renzo-tognella/decisionssearch/rule-blame)
Your own site
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/rule-blame"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/rule-blame/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 rule-blame

Your own site · 80×15
<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/rule-blame"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/rule-blame.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,446 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 $0.00091 $0.01446
Opus 5 $0.00046 $0.00723
Sonnet 5 $0.00018 $0.00289
Haiku 4.5 $0.00009 $0.00145

Measured 11d ago against content hash 04d96c6adbb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rule-blame 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 11d 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.

skills-memory/rule-blame/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rule Blame

Você é o Git Blame das regras de negócio: parte de uma BusinessRule resolvida e reconstrói como ela evoluiu, quais PRs a implementaram/modificaram e qual razão está realmente capturada. A regra permanece em prosa; o PR fornece a história operacional, arquivos e objetivo.

CORE RULE: Toda transição precisa de evidência: memory_id da regra, PRMemory, link ou rationale. Sem fonte, declarar lacuna; nunca deduzir uma versão apenas porque dois textos parecem semelhantes.

When to activate

  • Trigger phrases: "como essa regra chegou nesse estado?", "histórico da regra X", "que PRs mudaram essa regra?", "rule blame de Y"
  • Contexts: auditoria, conformidade ou investigação da evolução de uma regra

Do NOT activate for:

  • "tem regra sobre X?" → use query-memory
  • criar ou atualizar regra → use create-business-rule-memory
  • histórico de decisão arquitetural → use architecture-blame
  • motivação de um arquivo → use code-blame

Inputs

  • rule_ref (required): título, termo ou memory_id da regra. Fonte: usuário.

Context load

  • Carregar .decisionssearch/business.md para resolver taxonomia e macro-regras.
  • Verificar MCP DecisionsSearch com um memory.query trivial.

Procedure

  1. Resolver a regra — memory.query com type=BusinessRule + rule_ref.
    • Se houver mais de uma candidata plausível → listar e perguntar qual.
    • Se houver zero → dizer que a regra não existe no grafo e sugerir create-business-rule-memory.
  2. Percorrer versões — a partir da vigente, seguir DEPRECATES da versão nova para a anterior e REFINES quando a relação estiver verificada. Não inferir ordem por semelhança textual.
  3. Coletar PRMemory operacional — para cada versão, consultar memory.pr.linked_memories e identificar PRs com IMPLEMENTS, MODIFIES ou EVIDENCES. Para cada PR, conservar summary, objetivo em prosa e changed_files completos; se um arquivo for relevante à dúvida, buscar por arquivo primeiro e reranquear pelo resumo/objetivo.
  4. Coletar razão — consultar rationale do link/deprecate e episódios que referenciem a versão em related_memory_ids. Diferenciar explicitamente:
    • fato da BusinessRule;
    • mudança e objetivo do PR;
    • hipótese ou lacuna não capturada.
  5. Ordenar e delimitar — ordenar por event_date, mais recente primeiro, e indicar quando a data vem da regra, do PR ou do link. Não transformar uma mudança de implementação em mudança de regra sem evidência.
  6. Self-Refine gate — criticar contra:
    • cada versão tem memory_id e fonte?
    • cada PR tem summary/objetivo e link verificados?
    • a ordem bate com event_date?
    • razões sem reasoning/rationale estão marcadas como lacuna? Refine até todas as respostas serem "sim"; só então apresentar.
  7. Apresentar timeline — vigente no topo, versões anteriores abaixo, prosa curta por versão, arquivos/PRs relevantes e gaps explícitos.

Read the full file on GitHub · 125 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 125 lines · 91 tokens per session scan A 04d96c6adbb6

Subscribe to this mod's changes

rule-blame is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (1 stars, last pushed 18d ago), licensed MIT. It adds 91 tokens to every session and 1,446 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens