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-troubleshootgit 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-troubleshoot)<a href="https://agentmods.dev/commands/freshworks-developers/fw-dev-tools/fw-setup-troubleshoot"><img src="https://agentmods.dev/badge/commands/freshworks-developers/fw-dev-tools/fw-setup-troubleshoot.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 5.1 | $0.00036 | $0.03188 |
| Opus 5 | $0.00018 | $0.01594 |
| Sonnet 5 | $0.00007 | $0.00638 |
| Haiku 4.5 | $0.00004 | $0.00319 |
Grade E, and why
fw-setup-troubleshoot scanned grade E with 3 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.fdk Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDK setup — troubleshoot (/fw-setup-troubleshoot)
Universal FDK troubleshooter: Automated fix → Interactive manual SOP fallback. No retry loops, no support escalation.
Behaviour
| Intent | Execution | On Failure |
|---|---|---|
/fw-setup-troubleshoot |
Inline diagnostics — identify issues, suggest --fix or manual path |
N/A (diagnostic only) |
/fw-setup-troubleshoot --fix |
Automated repair Task — backup rc files, fix nvm/PATH/FDK | → Interactive SOP Mode |
Three-Phase Flow
Phase 1: Inline Diagnostics (No --fix)
Run diagnostics and interpret:
- Wrong Node active vs where
npm install -gputfdk(loadreferences/error-command-not-found.md) - nvm missing from
~/.zshrc/~/.bashrcorNVM_DIRwrong nvm alias default/fdkpointing at bare24instead of 24.11
Output: Diagnosis + recommendation (suggest --fix or manual steps based on complexity)
Phase 2: Automated Fix (With --fix)
Run Task (see below) that:
- Backs up dotfiles with timestamp
- Ensures nvm is loaded
- Installs/aligns Node 24.11 + FDK 10
- Verifies in clean shell
Success: Report completion, ask user to verify in NEW terminal
Failure: Automatically enter Phase 3 (Interactive SOP Mode)
Phase 3: Interactive SOP Mode (When --fix Fails)
Entry conditions:
--fixTask exits with error- User reports automation didn't work
- User explicitly asks for manual steps
Protocol:
- ✅ Load
references/interactive-troubleshooting-guide.md - ✅ Provide ONE diagnostic command at a time
- ✅ Wait for human to paste output
- ✅ Interpret output and provide NEXT specific command
- ✅ Adapt path based on actual results
- ❌ NEVER retry
--fixTask in loop - ❌ NEVER suggest "try again" without new information
- ❌ NEVER ask for diagnostic bundle or support escalation
Example transition to Phase 3:
⚠️ The automated fix encountered an issue:
FAILED: nvm not found at $HOME/.nvm/nvm.sh
Let's troubleshoot this manually step-by-step.
I'll guide you through diagnostic commands. Run each command and paste the output back.
**Step 1: Check if nvm is installed on your system**
Run:
ls -la ~/.nvm
Paste the output here.
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.
- 5d ago First seen · 345 lines · 36 tokens per session scan E 2b1d2764c869
fw-setup-troubleshoot is a command published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 3,188 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). 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.