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/fdk-fixgit clone --depth 1 https://github.com/freshworks-developers/fw-dev-toolsWhat 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 | $0.00046 | $0.01142 |
| Opus 5 | $0.00023 | $0.00571 |
| Sonnet 5 | $0.00009 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
fdk-fix 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDK Fix Command
Usage: /fdk-fix
You are fixing all platform validation errors and lint errors in a Freshworks app. Follow these steps exactly.
Step 1: Determine app directory
- Search the workspace for
manifest.jsonfiles. - If multiple folders contain manifest.json: Ask the user which app to fix.
- If one folder: Use that directory.
- If none: Inform the user and stop.
Step 2: Manifest + toolchain gate (before fdk validate)
Mandatory: Follow SKILL.md → Manifest + toolchain gate before any fdk validate.
- Shell not Node 24.x + FDK 10.x →
fw-setupfirst; do not lowerenginesor switch to FDK 9 / Node 18 to match the app. platform-versionnot3.0→ run/fdk-migratefirst, then continue this command at validation.3.0butenginesstill 18 / 9.x → raiseenginesper/fdk-migrateStep 3, then validate.[WARN] App engines major version mismatchwith FDK 10 + Node 24 active → alignmanifest.json→enginesupward to the CLI (or accept FDK’s sync prompt Y); never downgrade the toolchain.
Step 3: Run fdk validate
Toolchain: fw-app-dev does not install fdk or Node. If the shell has no fdk, wrong Node major for FDK 10, or only FDK 9.x while fixing a Platform 3.0 tree, follow SKILL.md (FDK / Node.js toolchain — not provided by fw-app-dev): use fw-setup when available, or prompt the user to add it (npx @freshworks/fw-dev-tools install). Do not invent one-off global npm installs here.
Run: cd <app-directory> && fdk validate
Capture all output (fatal errors, lint errors, warnings).
Step 4: Fix iteratively (up to 2 iterations for fatal, then lint)
Priority 1: Fatal errors (Platform/validation)
Fix these first. Use references/errors/ and rules/validation-workflow.mdc:
- JSON structure errors (multiple top-level objects, commas)
- Missing required files (icon.svg, iparams.json)
- Manifest structure (platform-version, modules, declarations)
- Request template errors (FQDN, path, schema)
- OAuth structure (integrations wrapper)
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 · 91 lines · 46 tokens per session scan A b775b7dee98d
fdk-fix is a command published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 1,142 once invoked, about $0.0002 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.
github-swarm
Create a specialized swarm for GitHub repository management.
self-healing
Automatically detect and recover from errors without interrupting your flow.
swarm-init
Initialize a Ruflo swarm with specified topology and configuration.
post-edit
Execute post-edit processing including formatting, validation, and memory updates.