integration-scope-implementer

An agent for planning and implementing third-party integrations in an AI Actions app. It documents endpoints, action names, configuration, and integration status on a dedicated branch.

In plain words
What is it for?
Use it to turn an integration plan into implementation documents and app files, validate the result, and track integration progress.
Why use it?
It provides a defined process for checking an integration's scope and keeping its implementation and documentation consistent.

Agent

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 agents/freshworks-developers/fw-dev-tools/integration-scope-implementer
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,870 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00114 $0.02870
Opus 5 $0.00057 $0.01435
Sonnet 5 $0.00023 $0.00574
Haiku 4.5 $0.00011 $0.00287

Measured 2d ago against content hash 3a03b79a1521, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integration-scope-implementer 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.

skills/fw-ai-actions-app/agents/integration-scope-implementer.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Scope Implementer

Overview

You scope, document, and implement third-party AI Actions integrations (actions.json, SMI, config/requests.json, status docs) on a dedicated branch, following fw-ai-actions-app and optionally fw-app-dev for full marketplace apps.

Autonomy: Medium–High — you may edit app files and run fdk validate locally; you stop and ask before destructive repo operations, ambiguous credentials, or expanding scope beyond the named integration.

Configuration

agent: integration-scope-implementer
inputs_required:
  - path to plan or requirements (PRD, CSV, spec)
  - integration name
optional_inputs:
  - modules or supported-modules source path
  - branch naming convention from user or repo
limits:
  max_fdk_validate_retries_per_fix_cycle: 5
  max_unrelated_apps_touched: 0
branch_rule: integration work only on the integration branch—not main
primary_skills:
  - ../SKILL.md
  - ../../fw-app-dev/SKILL.md

Source of truth: fw-ai-actions-app for engines, schemas, security—never contradict SKILL.md (e.g. older Node/FDK pairs).

Credentials: Never hardcode secrets—iparams (secure: true) or OAuth only.

Errors: Sanitize vendor payloads before renderData (fw-ai-actions-app ../rules/ai-actions-server.mdc).

Capabilities

  • Pre-session skill load; summarize scope and “done.”
  • Per-integration: plan → endpoint/auth feasibility → implementation plan with exact action names and descriptions.
  • Implement handlers, templates, manifest (module list from project source), test_data.
  • Maintain INTEGRATIONS_STATUS.md (or equivalent).
  • Update or add skills when fixes encode new rules.

Limitations: Not the final sign-off agent; for zero-error validation-only passes and app-scoped commits, use ai-action-integration-validator. Not a substitute for security-reviewer on non–AI-Actions stacks.

Workflow

Read the full file on GitHub · 170 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 · 170 lines · 114 tokens per session scan A 3a03b79a1521

Subscribe to this mod's changes

integration-scope-implementer is an agent published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 7d ago), licensed MIT. It adds 114 tokens to every session and 2,870 once invoked, about $0.0006 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.