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.
npx agentmods add commands/evol-ai/skillcompass/skill-updategit clone --depth 1 https://github.com/Evol-ai/SkillCompassWhat 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 | $0.00000 | $0.01432 |
| Opus 5 | $0.00000 | $0.00716 |
| Sonnet 5 | $0.00000 | $0.00286 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
skill-update 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skill-update — Check and Update Skills
Locale: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.
Check installed skills for remote updates and guide the user through updating and evaluating them.
Arguments
- (no args): list all skills that need checking and let the user choose
<skill-name>: check the specified skill for updatesall: check all git-repo-backed skills
Step 1: Load Inventory and Check Git Status
Use lib/update-checker.js to scan all skills:
const { UpdateChecker } = require('./lib/update-checker');
const checker = new UpdateChecker();
const stale = checker.getStale(inventory, 7); // not checked in last 7 days
const allGit = checker.checkAll(inventory); // all git-repo-backed skills
Execute via Bash node -e.
If no git-based skills found:
No git-repo-backed skills found; cannot check for updates.
For manually installed skills, check the source page for new versions.
Stop.
Step 2: Display and Select
If called with all: skip selection, check all git skills.
If called with <skill-name>: skip selection, check that skill only.
If called with no args: show the list and let user choose. Follow gstack's AskUserQuestion pattern — re-ground context, simplify, recommend, show options with effort scale.
{N} skills available to check for updates (git repo-backed):
1. code-review last checked: 12 days ago github.com/user/code-review
2. superpowers last checked: 9 days ago github.com/obra/superpowers
3. doc-writer last checked: 15 days ago github.com/user/doc-writer
4. ecc last checked: 8 days ago github.com/affaan-m/everything-claude-code
Checking updates requires network (git fetch), about 5 seconds each.
Enter a number, a name, or comma-separated list (e.g. 1,3), or type "all".
You can also type any other skill name directly.
[Check all / Select / Skip]
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.
- 2d ago First seen · 155 lines · 0 tokens per session scan A 8c49f46b49cb
skill-update is a command published in the GitHub repository Evol-ai/SkillCompass (215 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,432 tokens. 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.
Other commands, from other repositories
looper
Design and scaffold a Looper agent loop.
tma1-peer
List recent sessions on this project by agent — peers (Codex, OpenClaw, Copilot CLI) or your own.
monitor
Open the read-only web view of peers, threads and bus health.
send
Send a message to a peer session.
setup
Check that Devin Handoff is ready to use (dependencies + API key).
hard
Use subagents to plan and fix hard issues.