loci — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited loci (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use the loci CLI to manage tickets. The server does not need to be running — the CLI reads directly from disk.
loci list --jsonThis reveals the project prefix and all tickets. Use the prefix to confirm you are working in the right project.
loci get <id> --jsondescription.md: loci doc read <id> description.md --jsonloci doc write <id> description.md --content "<content>" loci patch <id> --assignee "agent:claude" --json
loci status <id> in_progress --jsonsuperpowers:using-superpowers skill to begin implementation.loci doc write <id> <filename>.md --content "<content>"loci doc write <id> summary.md --content "<content>"loci patch <id> --progress 100 --jsonloci status <id> in_review --json| Operation | Command | ||
|---|---|---|---|
| List tickets | loci list --json | ||
| Get ticket + all docs | loci get <id> --json | ||
| Create ticket | `loci add "title" [--priority low\ | medium\ | high] --json` |
| Update status | loci status <id> <status> --json | ||
| Update assignee / progress / priority / labels | loci patch <id> [--assignee <value>] [--progress <0-100>] [--priority <value>] [--labels <comma-list>] --json | ||
| Read a doc file | loci doc read <id> <filename> --json | ||
| Write a doc file | loci doc write <id> <filename> --content "<content>" | ||
| List attachments | loci attachments <id> --json |
Set assignee to null (unassigned): loci patch <id> --assignee null
Flow: todo → in_progress → in_review → done
| Status | Meaning |
|---|---|
todo | Not started |
in_progress | Actively being worked on |
in_review | Implementation complete, awaiting user verification |
done | Verified and closed — only set on explicit user confirmation |
| Value | Meaning |
|---|---|
null | Unassigned |
"human" | Project owner |
"agent:claude" | Claude AI agent |
"agent:<name>" | Any named AI agent |
| File | Purpose |
|---|---|
description.md | What the ticket is + acceptance criteria (always created) |
design.md | Technical or UI design decisions (optional) |
implementation_plan.md | Step-by-step plan (optional) |
summary.md | Post-completion summary (write before setting in_review) |
attachments.json | List of attached filenames (auto-managed) |
Any .md file in the ticket folder appears as a tab in the web UI.
low | medium (default) | high
Manual only — never auto-calculated. Range: 0–100.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.