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/derjochenmeyer/claude-code-craft-statusline/ongit clone --depth 1 https://github.com/derjochenmeyer/claude-code-craft-statuslineWhat 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 | $0.00015 | $0.00417 |
| Opus 5 | $0.00008 | $0.00209 |
| Sonnet 5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade B, and why
on scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
### 3. Patch ~/.claude/settings.json What it actually says
craft-statusline:on
Enable one of the craft-statusline boolean options. The argument is the field name.
Valid arguments
model, branch, context, context_alert, rate_limits, cost, color
Steps
1. Validate the argument
Argument is $ARGUMENTS. If empty or not in the list above, report:
Usage: /craft-statusline:on <field>
Valid fields: model, branch, context, context_alert, rate_limits, cost, color
Stop.
case "$ARGUMENTS" in
model|branch|context|context_alert|rate_limits|cost|color) ;;
*)
echo "Usage: /craft-statusline:on <field>"
echo "Valid fields: model, branch, context, context_alert, rate_limits, cost, color"
exit 1
;;
esac
2. Map to option key
Prepend show_ (e.g. cost → show_cost).
3. Patch ~/.claude/settings.json
User-config values for plugins live under pluginConfigs.<plugin-id>.options.
key="show_$ARGUMENTS"
existing=~/.claude/settings.json
[[ -f "$existing" ]] || echo '{}' > "$existing"
tmp=$(mktemp)
jq --arg k "$key" '
.pluginConfigs //= {}
| .pluginConfigs["craft-statusline"] //= {}
| .pluginConfigs["craft-statusline"].options //= {}
| .pluginConfigs["craft-statusline"].options[$k] = true
' "$existing" > "$tmp" && mv "$tmp" "$existing"
4. Confirm
Enabled: show_<field>
The change takes effect on the next status line refresh.
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.
- 3d ago First seen · 65 lines · 0 tokens per session scan B cb94bdf32d47
on is a command published in the GitHub repository derjochenmeyer/claude-code-craft-statusline (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 417 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
ask
Ask a peer session a question and wait for its answer.
setup
Prepare the current project for UIForge — ensure shadcn init, the component registries (shadcn + @motion-primitives), and the motion/lucide-react/cn prerequisites.
init
Initialize project documentation, preferences, or design tokens.
ace:status
Quick project status check with compact output.
kerberos
Kerberos attacks — AS-REP roasting and Kerberoasting.