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/freshworks-developers/fw-dev-tools/fw-setup-statusgit clone --depth 1 https://github.com/freshworks-developers/fw-dev-toolsWrote 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/freshworks-developers/fw-dev-tools/fw-setup-status)<a href="https://agentmods.dev/commands/freshworks-developers/fw-dev-tools/fw-setup-status"><img src="https://agentmods.dev/badge/commands/freshworks-developers/fw-dev-tools/fw-setup-status.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 | $0.00023 | $0.01020 |
| Opus 5 | $0.00012 | $0.00510 |
| Sonnet 5 | $0.00005 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
fw-setup-status 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 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.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDK setup — status (/fw-setup-status)
/fw-setup status. Read-only; no shell Task.
Behaviour
| User intent | Action |
|---|---|
/fw-setup-status |
Run the default block below (short summary). |
/fw-setup-status --verbose |
Run default then the verbose block (PATH, nvm, npm prefix, shell hints). |
Execution (default)
Run checks directly (no subagent):
echo "=== FDK Status ==="
echo "Node: $(node --version 2>&1 || echo 'Not installed')"
echo "nvm: $(nvm --version 2>&1 || echo 'Not installed')"
echo "FDK binary: $(command -v fdk || echo 'Not on PATH')"
echo "FDK cache: $([ -d ~/.fdk ] && echo 'Present (~/.fdk)' || echo 'Not found')"
# FDK version - diagnose PATH/Node mismatch if version check fails
if command -v fdk >/dev/null 2>&1; then
FDK_PATH=$(command -v fdk)
FDK_OUT=$(fdk version 2>&1)
FDK_EXIT=$?
if [ $FDK_EXIT -eq 0 ]; then
# Success - extract version (handles both "Installed: X.Y.Z" and "X.Y.Z" formats)
FDK_VER=$(echo "$FDK_OUT" | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1)
echo "FDK version: $FDK_VER"
else
# Failed - diagnose Node/npm prefix mismatch
echo "FDK version: Binary at $FDK_PATH but 'fdk version' failed"
echo " Current Node: $(node --version 2>&1 || echo 'not found')"
echo " npm prefix: $(npm config get prefix 2>&1 || echo 'not found')"
echo ""
echo " DIAGNOSIS: Node version mismatch (FDK installed on different Node version)"
echo " → Load references/error-command-not-found.md for fix"
fi
else
echo "FDK version: Not installed"
fi
echo "=================="
Execution (--verbose)
After the default block, run (still inline, no Task). On Windows PowerShell, run the PowerShell equivalents from references/windows.md (e.g. where.exe fdk, $env:Path -split ';') — the block below is Unix-style for bash/zsh.
echo ""
echo "=== FDK Status (verbose) ==="
echo "--- PATH (first 800 chars) ---"
echo "$PATH" | head -c 800
echo ""
echo "--- node / npm ---"
command -v node 2>/dev/null; command -v npm 2>/dev/null
npm config get prefix 2>/dev/null || true
echo "--- nvm ---"
export NVM_DIR="${NVM_DIR:-$HOME/.nvm}"
if [ -s "$NVM_DIR/nvm.sh" ]; then
. "$NVM_DIR/nvm.sh"
nvm current 2>/dev/null || true
nvm alias 2>/dev/null || true
else
echo "nvm.sh not sourced in this shell (NVM_DIR=$NVM_DIR)"
fi
echo "--- fdk candidates ---"
type -a fdk 2>/dev/null || true
NPF="$(npm config get prefix 2>/dev/null)"
[ -n "$NPF" ] && ls -la "$NPF/bin/fdk" 2>/dev/null || true
echo "--- shell rc (nvm lines only) ---"
for rc in "$HOME/.zshrc" "$HOME/.bashrc" "$HOME/.profile"; do
[ -f "$rc" ] || continue
echo "# $rc"
grep -nE 'NVM_DIR|nvm\\.sh|nvm use|freshworks|fdk' "$rc" 2>/dev/null || echo "(no matching lines)"
done
echo "============================"
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 · 95 lines · 23 tokens per session scan A 893033088b19
fw-setup-status is a command published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 9d ago), licensed MIT. It adds 23 tokens to every session and 1,020 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
bottleneck-detect
Analyze performance bottlenecks in swarm operations and suggest optimizations.
auto-agent
Automatically route a task to the optimal agent using Q-Learning. There is no auto agent family in v3 — the closest live surface is route, backed by swarm coordinate / autopilot for full multi-agent orchestration.
self-healing
Automatically detect and recover from errors without interrupting your flow.
swarm-init
Initialize a Ruflo swarm with specified topology and configuration.
post-task
Execute post-task cleanup, performance analysis, and memory storage.
code-review
Automated code review with swarm intelligence.