audit-trail

audit-trail is a command for Claude Code from doncheli/don-cheli-sdd. It costs 74 tokens per session (1,613 once invoked), scanned A, original, Apache-2.0.

An audit log for decisions made with AI during a project. It records what was generated, approved, changed, rejected, or reviewed, along with the actor and related file or pull request when available.

In plain words
What is it for?
Use it to record or inspect decisions, filter entries by action, artefact, or date, and export the log as a CSV file.
Why use it?
It provides a history of how project decisions were made, which helps with reviews, audits, and post-mortems.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the don-cheli-sdd plugin — 28 skills, 115 commands, 1 agent shipped together

Good fit Use it to record or inspect decisions, filter entries by action, artefact, or date, and export the log as a CSV file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/doncheli/don-cheli-sdd/audit-trail
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.

Clone the repo
git clone --depth 1 https://github.com/doncheli/don-cheli-sdd

Made for: Claude Code.

Or install don-cheli-sdd, the plugin that ships this one along with the rest of its 28 skills, 115 commands, 1 agent.

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 audit-trail

README.md
[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/audit-trail.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/audit-trail)
Your own site
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/audit-trail"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/audit-trail.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,613 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 $0.00074 $0.01613
Opus 5 $0.00037 $0.00807
Sonnet 5 $0.00015 $0.00323
Haiku 4.5 $0.00007 $0.00161

Measured 5d ago against content hash f1452b3ce8ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-trail 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.

scripts/.claude/commands/dc/audit-trail.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dc:audit-trail

Objetivo

Registrar, almacenar y consultar todas las decisiones asistidas por IA durante el ciclo de vida del proyecto: qué se generó, qué se aprobó, qué se modificó y por quién. Proporciona trazabilidad completa para auditorías, revisiones y post-mortems.

Uso

/dc:audit-trail                            # Ver entradas recientes (últimas 20)
/dc:audit-trail --registrar                # Registrar acción actual
/dc:audit-trail --filtro accion=generate   # Filtrar por tipo de acción
/dc:audit-trail --filtro artefacto=spec    # Filtrar por tipo de artefacto
/dc:audit-trail --filtro fecha=2026-03-28  # Filtrar por fecha
/dc:audit-trail --exportar csv             # Exportar como CSV
/dc:audit-trail --resumen                  # Estadísticas del proyecto

Comportamiento

1. REGISTRAR — Capturar entrada en el log
   ├── Timestamp UTC con timezone local
   ├── Tipo de acción: generate | approve | modify | reject | review
   ├── Artefacto afectado: spec | test | code | review | plan | config
   ├── Resumen (≤ 120 chars) de qué se hizo
   ├── Actor: ia | human | ci
   └── Referencia a archivo o PR si aplica

2. ALMACENAR — Persistir en .dc/audit-trail.md
   ├── Formato Markdown + YAML front-matter por entrada
   ├── Append-only (nunca modificar entradas existentes)
   └── Rotar archivo cuando supere 5,000 líneas → audit-trail-archive/

3. CONSULTAR — Filtrar y mostrar entradas
   ├── Soportar filtros combinables por fecha, acción y artefacto
   ├── Paginación: 20 entradas por página
   └── Modo resumen: estadísticas agregadas

Estructura de Entrada

---
id: AT-0047
timestamp: 2026-03-28T14:32:11-03:00
action: generate        # generate | approve | modify | reject | review
artifact: spec          # spec | test | code | review | plan | config
actor: ia               # ia | human | ci
summary: "Generado spec Gherkin para feature ReembolsosParciales (3 escenarios)"
ref: specs/features/pagos/reembolsos.feature
session: dc-session-2026-03-28-a
---

Read the full file on GitHub · 136 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 · 136 lines · 74 tokens per session scan A f1452b3ce8ff

Subscribe to this mod's changes

audit-trail is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,613 once invoked, about $0.0004 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 2026-09-03.