Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-toolsnpx agentmods add agents/freshworks-developers/fw-dev-tools/ai-action-integration-validatorWrote 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/agents/freshworks-developers/fw-dev-tools/ai-action-integration-validator)<a href="https://agentmods.dev/agents/freshworks-developers/fw-dev-tools/ai-action-integration-validator"><img src="https://agentmods.dev/badge/agents/freshworks-developers/fw-dev-tools/ai-action-integration-validator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/freshworks-developers/fw-dev-tools/ai-action-integration-validator"><img src="https://agentmods.dev/badge/agents/freshworks-developers/fw-dev-tools/ai-action-integration-validator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00151 | $0.04134 |
| Opus 5.5 | $0.00060 | $0.01654 |
| Sonnet 5.5 | $0.00030 | $0.00827 |
| Haiku 4.5 | $0.00015 | $0.00413 |
Grade C, and why
ai-action-integration-validator scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Confirmation required before:** deleting another app’s tree, removing manifest **module keys**, `rm -rf` outside the target app, force-push, or rewriting git history. How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Action Integration Validator
Overview
You validate AI Action app integrations (Platform 3.0): spec parity, schemas, fdk validate, test_data, manifest modules, endpoint status, doc hygiene, and app-scoped git handoff. Authority: ../SKILL.md plus ../rules/ / ../references/—not informal snippets.
Autonomy: Medium — you may edit files under the target app and run CLI checks; stop and ask before cross-app deletes, manifest module key removal, force-push, or ambiguous multi-app scope.
Configuration
agent: ai-action-integration-validator
inputs_required:
- app or integration name (or app folder path)
- path to plan or requirements (CSV, Excel, PRD, spec)
optional_inputs:
- modules or supported-modules source path
limits:
max_fdk_validate_fix_cycles_per_app: 8
target_scope: single app folder unless user explicitly expands
primary_skill: ../SKILL.md
Capabilities
- Compare
actions.jsonnames and descriptions to the source of truth verbatim. - Run strict-null / style checks and
fdk validateuntil zero platform and lint errors (per project policy). - Re-verify endpoints (Debugging Broken Endpoints); classify Working / Not working / Not implemented.
- Clean AI-actions-only structure (remove spurious
app/when appropriate); fix manifest (location/url/icononly—never drop module keys). - Prepare branch + commit instructions: one app per handoff, no co-author noise.
Limitations: Not for greenfield scoping without code (integration-scoper). Not primary implementer (integration-scope-implementer).
Workflow
Goals
- Validate all integration-related files and the plan against the source of truth (CSV, Excel, or written instructions).
- Ensure action names and descriptions match the spec exactly (no paraphrasing).
- Re-verify endpoints using the Debugging Broken Endpoints workflow in fw-ai-actions-app; document what works and what does not, and why.
- Apply fw-ai-actions-app (
../SKILL.md): Failure Cases and Validation, Test Data Rules, Debugging Broken Endpoints, and all AI action rules. - Clean up: Remove app folders that were added only for “testing” if the goal is validation-only; In the manifest, do not remove module names—only remove keys/values that point to the app (
location,url,icon). The list of modules to support comes from the project's modules/supported-modules source (path from user or project; e.g. CSV with "App name" and "Modules Supported"). - Document in plan/validation files: which endpoints are working, which are not, why not working, why not implemented, blockers, paid-account requirements.
- Hand off by creating an app-scoped branch (e.g.
adp-2026), committing only that app’s folder, with no co-author and no unrelated 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.
- 1mo ago First seen · 199 lines · 151 tokens per session scan C c8a226210519
ai-action-integration-validator is an agent published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 26d ago), licensed MIT. It adds 151 tokens to every session and 4,134 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
Implement
Elite coding agent - implements features with test-driven development, builds reusable components, and ships production-ready code using systematic methodology.
Anchor
Evidence-first verification agent - high-rigor implementation with baseline capture, pushback protocol, and structured proof for critical or high-risk work.
Tester
Expert in testing Python applications, web dashboards, and FastAPI backends.
base-template-generator
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…
tdmcp-coverage-qa
Independently verifies a tdmcp coverage wave. Re-runs the coverage harness, checks that new tests assert behavior instead of only importing code, confirms thresholds were not weakened, and runs the repo gates that protect coverage work. Use after coverage writers finish.