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 instructions/freshworks-developers/fw-dev-tools/agents-mdgit 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 | $0.02599 | $0.02599 |
| Opus 5 | $0.01300 | $0.01300 |
| Sonnet 5 | $0.00520 | $0.00520 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
fw-dev-tools AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — marketplace repo (contributors)
Repo-only document. Not shipped by the installer. End developers receive a slim routing spec (installer/src/specs/fw-dev-tools-spec.md) written to always-loaded IDE locations — not this file.
| Audience | Read first |
|---|---|
| Contributing to this repo | This file → CONTRIBUTING.md → tests/TESTING.md |
| Building a Freshworks app (any project) | skills/*/SKILL.md + installed fw-dev-tools.mdc / spec block |
| Humans (overview, install) | README.md · TROUBLESHOOTING.md · docs/engine-matrix.md (FDK/Node pins) |
Before you open a PR
cd tests && npm install && npm test # static tests (CI, no LLM)
cd installer && npm install && npm test # installer lifecycle tests (CI, Node 24)
Skill / command / .meta.template.json edits — also run behavioral evals locally (no API key in agent session):
"Run the skill evals"
Attach tests/all-tests-report.html to the PR. See tests/TESTING.md for all layers (static, eval, e2e).
PR checklist: .github/PULL_REQUEST_TEMPLATE.md
If you change…
| You change | Also update | Verify |
|---|---|---|
skills/*/rules/ or skills/*/commands/ |
Rules and commands inventory (below) + .cursor-plugin/marketplace.json / .claude-plugin/marketplace.json rulesPath / commandsPath |
cd tests && npm test |
skills/*/SKILL.md behavioral gates |
tests/eval/skill-eval-scenarios.js + tests/TESTING.md scenario table |
cd tests && npm run eval |
skills/shared/.meta.template.json or meta scripts |
All skills referencing meta-init.sh / meta-update.sh |
cd tests && npm test |
skills/fw-setup toolchain guidance |
docs/engine-matrix.md |
cd installer && npm test |
installer/ |
installer/tests/ |
cd installer && npm test |
| Plugin manifests | Skill inventory below stays aligned | static tests (plugin version consistency) |
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 · 172 lines · 2,599 tokens per session scan A 9f59dc0fc75b
fw-dev-tools AGENTS.md is an instructions file published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It adds 2,599 tokens to every session, about $0.0130 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 instructions, from other repositories
agent-skills AGENTS.md
Instructions for sayeed1999/agent-skills, covering agents.md, output style, output style, 1. think before code and 2. simplicity.
agent-skills CLAUDE.md
Instructions for sayeed1999/agent-skills, covering claude.md, output style, 1. think before code, 2. simplicity and 3. architecture boundaries (clean architecture).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.