# Trace

> Read or hand-write the project progress ledger (.claude/trace.md). Use when the user says "/trace", "what did I do", "log this", "trace done", or wants to record or review what moved this session. The automatic Stop hook already logs file changes; this skill is the reader and the manual writer for the intent the hook cannot infer.

- **Type:** Skill
- **Install:** `agentstack add skill-mirkobozzetto-arsenal-trace`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mirkobozzetto](https://agentstack.voostack.com/s/mirkobozzetto)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mirkobozzetto](https://github.com/mirkobozzetto)
- **Source:** https://github.com/mirkobozzetto/arsenal/tree/main/plugins/trace/skills/trace

## Install

```sh
agentstack add skill-mirkobozzetto-arsenal-trace
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# trace

One ledger: `/.claude/trace.md`. The Stop hook writes mechanical
entries automatically (which files changed, each turn that touched files). This
skill is the **reader** and the **manual writer** for the *why* the hook cannot
infer. It never invents a second format - it shells out to the same script.

## Routing

Let `S` = `${CLAUDE_PLUGIN_ROOT}/skills/trace/scripts/trace.cjs`. Run from the
project root (so the ledger and git detection resolve to this repo).

- **`/trace`** (no args) -> read recent entries:
  ```bash
  node "$S" --read 12
  ```
  Print the output as-is. Do not summarize unless asked.

- **`/trace done  [flags]`** -> write one clean entry:
  ```bash
  node "$S" done "" [--files a,b] [--id N.x] [--status shipped|in_progress|wip] [--context prd:]
  ```
  Map the user's words to ``. Pass `--files` when they name files,
  `--id` for a prd Unit (`N.x`) or rfc task (`T0n`), `--status shipped` when the
  work is truly done and verified (default `wip`). Context is inferred from the
  files when omitted.

- **Anything else after `/trace`** -> treat the free text as the `` of a
  `done` entry, status `wip`, unless the user clearly meant to read.

## Notes

- The hook covers automatic capture; only reach for `done` when the user wants
  to record intent ("note that I finished the auth refactor") that bare file
  paths do not convey.
- `--status shipped` is a claim of verified-done, not attempted. Use the user's
  evidence, do not upgrade a `wip` to `shipped` on your own.
- For the entry format and how this relates to ship's per-run `trace.md`, see
  [references/format.md](references/format.md).

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mirkobozzetto](https://github.com/mirkobozzetto)
- **Source:** [mirkobozzetto/arsenal](https://github.com/mirkobozzetto/arsenal)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mirkobozzetto-arsenal-trace
- Seller: https://agentstack.voostack.com/s/mirkobozzetto
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.