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/add-servergit 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 | $0.00019 | $0.00494 |
| Opus 5 | $0.00010 | $0.00247 |
| Sonnet 5 | $0.00004 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
add-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Add Server
set -euo pipefail
source "${CLAUDE_PLUGIN_ROOT:-plugin}/commands/_fleet-lib.sh"
mkdir -p "$FM_SERVERS_DIR"
NAME="$(printf '%s' "$ARGUMENTS" | tr -d '[:space:]')"
if [ -n "$NAME" ] && profile_exists "$NAME"; then
echo "RE_ADD: server '$NAME' already exists"
fi
Re-Add protection (Concern 1): If the script prints RE_ADD: …, the server
already exists. Do not overwrite it blindly (that would lose Scoped Operations,
Protected Resources and Notes). Ask the user via AskUserQuestion:
"Server <name> existiert. Was tun?" → Options:
- "Aktiv setzen (
/use)" → runset_active <name>; write_inventoryand stop. - "Update-Modus" → update only the Connection section + newly discovered Identity/Discovered-State fields; preserve Scoped Operations, Protected Resources and Notes.
- "Abbrechen".
Otherwise (new server): run the intake dialogue from /first-run step 1
yourself, here in the main thread, then dispatch the fleet-intake subagent with
the collected values exactly as /first-run step 2 describes, and handle its
return value as /first-run step 3 describes.
The subagent has no AskUserQuestion tool — subagents cannot reach the user — so
it must never be dispatched before every answer is in hand.
Two differences from /first-run:
- The inventory is not empty, so
<name>must not collide with an existing profile. The bash block above already reports a collision for an argument-supplied name; re-check withprofile_existsafter the dialogue if the user typed a different one. - Do not assume the new server should become active. Dispatch with
set_active=no, then ask viaAskUserQuestionafter a successful intake, and only runset_active <name>; write_inventoryif the user says yes.
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 · 46 lines · 19 tokens per session scan A cb8538e546c6
add-server is a command published in the GitHub repository CallMeTechie/fleet-manager (1 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 494 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
dns-provider
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
cloud
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
instances
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
deploy-static
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
cluster
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.