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/diaggit clone --depth 1 https://github.com/CallMeTechie/fleet-managerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/callmetechie/fleet-manager/diag)<a href="https://agentmods.dev/commands/callmetechie/fleet-manager/diag"><img src="https://agentmods.dev/badge/commands/callmetechie/fleet-manager/diag.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00025 | $0.00792 |
| Opus 5 | $0.00013 | $0.00396 |
| Sonnet 5 | $0.00005 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade B, and why
diag scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# 2. Passwordless sudo if "${FM_SSH[@]}" "sudo -n true 2>/dev/null"; then What it actually says
Diag
set -euo pipefail
source "${CLAUDE_PLUGIN_ROOT:-plugin}/commands/_fleet-lib.sh"
NAME="$(resolve_server "$(printf '%s' "$ARGUMENTS" | tr -d '[:space:]')")"
build_ssh "$NAME"
echo_target "$NAME"
echo "── Diagnostics ──"
# 1. SSH reachability
if "${FM_SSH[@]}" "echo OK" 2>/dev/null | grep -qx OK; then
echo "PASS SSH reachable"
else
echo "FAIL SSH unreachable — run /setup-ssh $NAME (key not deployed?), check port/host."
exit 1
fi
# 2. Passwordless sudo
if "${FM_SSH[@]}" "sudo -n true 2>/dev/null"; then
echo "PASS passwordless sudo available"
else
echo "WARN no passwordless sudo (privileged ops need a NOPASSWD sudoers drop-in)"
fi
# 3. Docker presence + working invocation (probe order: no-sudo, sudo, abs paths)
DOCKER_CMD=""
for cand in "docker" "sudo -n docker" "sudo -n /usr/local/bin/docker" "/usr/local/bin/docker"; do
if "${FM_SSH[@]}" "$cand info --format '{{.ServerVersion}}' 2>/dev/null" | grep -q '^[0-9][0-9]*\.[0-9]'; then
DOCKER_CMD="$cand"; break
fi
done
if [ -n "$DOCKER_CMD" ]; then
echo "PASS docker present (via: $DOCKER_CMD)"
else
echo "WARN docker not found (Phase 2 compose features unavailable)"
fi
# 4. Disk usage (root fs) — capture first so a transient SSH error here does NOT
# abort the whole command under `set -e`/`pipefail` after step 1 passed (C1).
if disk_out="$("${FM_SSH[@]}" "df -h / | tail -1" 2>/dev/null)"; then
printf '%s\n' "$disk_out" | awk '{print "INFO disk / used "$5" ("$3"/"$2")"}'
else
echo "WARN disk query failed (transient SSH error?)"
fi
# 5. Load
if up_out="$("${FM_SSH[@]}" "uptime" 2>/dev/null)"; then
printf '%s\n' "$up_out" | sed 's/^/INFO /'
else
echo "WARN uptime query failed"
fi
After printing, update the Discovered State section and the UTC Last Updated
line of context/servers/<name>.md (use the lib's sanitize_value on stored values).
Also persist the docker probe: set docker_available to yes/no and docker_cmd
to $DOCKER_CMD (or _not configured_). Lazy migration for pre-Phase-2 profiles
that lack the docker_cmd line — insert it after - docker_available::
if ! grep -q '^- docker_cmd:' "$PROFILE"; then
TMP_P="$(mktemp)"
awk '/^- docker_available:/ { print; print "- docker_cmd: _not configured_"; next } { print }' "$PROFILE" > "$TMP_P" && mv "$TMP_P" "$PROFILE"
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.
- 3d ago First seen · 73 lines · 25 tokens per session scan B d864f806ebaa
diag is a command published in the GitHub repository CallMeTechie/fleet-manager (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 792 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
remote-autopilot-install.v1
Remotely install Stakpak Autopilot on any reachable Linux host over SSH, with optional AWS/GCP/Azure VM discovery or provisioning: /remote-autopilot-install.
deploy
You are tasked with deploying the mcp-server-langgraph application to various targets. This command.
cost-optimize
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with cost optimize in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
terraform-scaffold
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with terraform scaffold in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
cost-optimize
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with cost optimize in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
terraform-scaffold
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with terraform scaffold in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.