fw-dev-tools AGENTS.md

Repository instructions for contributors to the Freshworks developer-tools marketplace and guidance for developers building Freshworks apps.

In plain words
What is it for?
Use them to find the correct instructions, repository layout, slash commands, test commands, engine versions, and pull-request checks.
Why use it?
They clarify which documents and tests apply to contributors, app builders, and end users, preventing repository-only guidance from being shipped by the installer.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/freshworks-developers/fw-dev-tools/agents-md
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools

Made for: Codex, OpenCode.

Per session 2,599 This file is loaded in full into every session.
When invoked 2,599 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 9f59dc0fc75b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 172 lines

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.mdtests/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)

Read the full file on GitHub · 172 lines

Changes

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.

  1. 2d ago First seen · 172 lines · 2,599 tokens per session scan A 9f59dc0fc75b

Subscribe to this mod's changes

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.

Related

Other instructions, from other repositories