A project progress ledger stored in `.claude/trace.md`. It records file changes automatically and lets you add or review the reasons and work behind them.

Use it to read recent project activity, record completed or ongoing work, and attach notes such as changed files, task identifiers, status, or brief context.

It keeps a durable record of what changed during coding sessions, including context that automatic file tracking cannot determine. This helps you remember and review progress without maintaining a separate log.

trace — Skill for Claude Code by mirkobozzetto/arsenal

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 mirkobozzetto/arsenal --skill trace

Clone the repo

git clone --depth 1 https://github.com/mirkobozzetto/arsenal

Made for: Claude Code.

Or install trace, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mirkobozzetto/arsenal/trace/github.svg)](https://agentmods.dev/skills/mirkobozzetto/arsenal/trace)

Your own site

<a href="https://agentmods.dev/skills/mirkobozzetto/arsenal/trace"><img src="https://agentmods.dev/badge/skills/mirkobozzetto/arsenal/trace/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mirkobozzetto/arsenal/trace"><img src="https://agentmods.dev/badge/skills/mirkobozzetto/arsenal/trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 708 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00708
Opus 5.5	$0.00011	$0.00283
Sonnet 5.5	$0.00006	$0.00142
Haiku 4.5	$0.00003	$0.00071

Measured 24d ago against content hash 1007cd8b2de9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trace 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 24d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/trace.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/trace/skills/trace/SKILL.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.

Trace

Run at the end of a session the user wants to close, before /clear. It leaves a dated save that next offers to resume. Trace never resumes work itself. Resolve scripts/trace.cjs from this skill's directory.

Save (no argument, or `save`)

Gather, without asking: this conversation; git log since the last save (node scripts/trace.cjs saves --all gives its date); git status --short; planned work: briefs (docs/brief/*/brief.md) and proposals (docs/proposals/*/PROPOSAL.md) not shipped or superseded, review reports (docs/review/*/report.md) with unchecked points, and open issues from gh issue list --label arsenal --state open when gh answers.
Show at most five lines: done, not finished, planned.
Ask only what the context cannot answer, one question per message, in plain text and the conversation language, then wait:
- what to continue next session, with your suggestion;
- anything to remember that you may have missed: a decision, an approach that failed. Skip a question the conversation already answers. Usually none is needed.
Write it: node scripts/trace.cjs save --done "…" --left "…" --next "a ; b" --remember "…" --planned "…". One line per field, in the conversation language, specific: paths, branch, task ids, issue numbers, commands. Omit an empty field. The save closes older open saves on the same branch (superseded): carry into it whatever they still left.
End with « Tu peux /clear. » in the conversation language, then the resume command as the last line: next in the harness syntax (/next:next in Claude Code, /skill:next in OMP and Pi, $next in Codex).

The save is private: the script adds the ledger to .git/info/exclude and it never enters a commit.

Other modes

done "<what>" [--files a,b] [--id id] [--status shipped]: one intent entry. shipped only with evidence.
--read n: print the last entries, then stop. Do not reopen the work they describe.

Read the full file on GitHub · 59 lines

Files

What ships with it

2 files 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.

24d ago Changed · +1 lines 1007cd8b2de9
1mo ago Changed · +33 lines · +13 tokens per session badcb5480399
2mo ago Changed · -23 lines · -61 tokens per session 3af5384898db
2mo ago First seen · 48 lines · 76 tokens per session scan A 0aabc1a6876e

Subscribe to this mod's changes

trace is a skill published in the GitHub repository mirkobozzetto/arsenal (23 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 708 once invoked, about $0.0001 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 2026-08-30.

Claude Code Project management ai-agents claude-skills codex cursor exa

trace next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tracemirkobozzetto/arsenal	Skill	23	10d ago	MIT	A	28	Claude Code
create-video-seedance-2-falgooseworks-ai/goose-skills	Skill	1.3k	6d ago	MIT	A	121	Claude Code, Codex
meta-ad-managergooseworks-ai/goose-skills	Skill	1.3k	6d ago	MIT	A	108	Codex
create-chatgpt-mockupgooseworks-ai/goose-skills	Skill	1.3k	6d ago	MIT	A	90	Claude Code, Codex
run-memorygooseworks-ai/goose-skills	Skill	1.3k	6d ago	MIT	A	72	Claude Code, Codex
company-contact-findergooseworks-ai/goose-skills	Skill	1.3k	6d ago	MIT	A	55	Claude Code, Codex
review-finished-adgooseworks-ai/goose-skills	Skill	1.3k	6d ago	MIT	A	200	Claude Code, Codex