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.
Install
$ agentstack add skill-mirkobozzetto-arsenal-trace ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-mirkobozzetto-arsenal-trace) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
donewhen the user wants
to record intent ("note that I finished the auth refactor") that bare file paths do not convey.
--status shippedis 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
- Source: mirkobozzetto/arsenal
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.