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/callmetechie/fleet-manager/logsgit clone --depth 1 https://github.com/CallMeTechie/fleet-managerWhat 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 | $0.00029 | $0.00654 |
| Opus 5 | $0.00015 | $0.00327 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
logs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Logs
/logs reads the system journal. For a container/app log use /compose-logs <project>.
set -euo pipefail
source "${CLAUDE_PLUGIN_ROOT:-plugin}/commands/_fleet-lib.sh"
TAIL=100; UNIT=""; SERVER_ARG=""
set -f # no globbing of unquoted $ARGUMENTS (review H2)
# shellcheck disable=SC2086 # intentional: split ARGUMENTS into positional params
set -- ${ARGUMENTS:-}
while [ $# -gt 0 ]; do
case "$1" in
--tail) shift; TAIL="${1:-100}" ;;
--tail=*) TAIL="${1#*=}" ;;
--*) echo "Unknown flag: $1" >&2; exit 1 ;;
*) if [ -z "$SERVER_ARG" ]; then SERVER_ARG="$1"; else UNIT="$1"; fi ;;
esac
shift
done
[[ "$TAIL" =~ ^[0-9]+$ ]] || { echo "Invalid --tail" >&2; exit 1; }
if [ -n "$UNIT" ]; then [[ "$UNIT" =~ ^[A-Za-z0-9@._-]+$ ]] || { echo "Invalid unit" >&2; exit 1; }; fi
NAME="$(resolve_server "$SERVER_ARG")"
build_ssh "$NAME"; echo_target "$NAME"
is_scope_authorized "$NAME" system_monitoring || {
echo "REFUSED: scope 'system_monitoring' not authorized for '$NAME'." >&2; exit 1; }
if "${FM_SSH[@]}" "command -v journalctl >/dev/null 2>&1"; then
if [ -n "$UNIT" ]; then JC="journalctl -n $TAIL -u $UNIT --no-pager"; else JC="journalctl -n $TAIL --no-pager"; fi
OUT="$("${FM_SSH[@]}" "$JC 2>&1" || true)"
if echo "$OUT" | grep -qiE "permission denied|not seeing messages from other users"; then
echo "WARN journalctl permission denied — add the SSH user to the 'systemd-journal' or 'adm' group." >&2
fi
if [ -z "$OUT" ] && [ -n "$UNIT" ]; then
echo "(no journal entries for unit '$UNIT' — for container logs try: /compose-logs $UNIT)"
else
printf '%s\n' "$OUT"
fi
else
echo "(journalctl not present — falling back to /var/log/syslog)"
"${FM_SSH[@]}" "tail -n $TAIL /var/log/syslog 2>/dev/null" || echo "(no /var/log/syslog either)"
fi
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.
- yesterday First seen · 52 lines · 29 tokens per session scan A 47e49049374b
logs is a command published in the GitHub repository CallMeTechie/fleet-manager (1 stars, last pushed 29d ago), licensed MIT. It adds 29 tokens to every session and 654 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
cleanup
Clean up TTS cache files to free up disk space.
deps-age
Analyze dependency freshness and maintenance activity.
release-prep
Automated release readiness validation.
review-pr
Comprehensive PR review checklist to ensure code quality, testing, and best practices.