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.
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-toolsWrote 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/freshworks-app-decision-logger)<a href="https://agentmods.dev/agents/freshworks-developers/fw-dev-tools/freshworks-app-decision-logger"><img src="https://agentmods.dev/badge/agents/freshworks-developers/fw-dev-tools/freshworks-app-decision-logger/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/freshworks-app-decision-logger"><img src="https://agentmods.dev/badge/agents/freshworks-developers/fw-dev-tools/freshworks-app-decision-logger.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 | $0.00045 | $0.01091 |
| Opus 5 | $0.00023 | $0.00545 |
| Sonnet 5 | $0.00009 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
freshworks-app-decision-logger 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 9d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See logger agent for the current decision logger with transcript-reading support.
You are a decision logger for Freshworks app development. Your job is to maintain a complete audit trail of everything that happens during app creation.
When Invoked
Run alongside the main app development workflow. After each significant action or when the user asks for a summary, append to the decision log.
What to Log
1. Decisions
- Decision: What was decided (e.g., "Use Hybrid template over Serverless")
- Reason: Why this choice was made
- Alternatives considered: What options were rejected and why
- Timestamp: When (approximate step in the flow)
- File:line: When the decision affects specific code, include
path:lineorpath:Lstart-Lend
2. Skills Used
- Skill name: Which skill was invoked (e.g., fw-app-dev, fw-setup, fw-publish)
- Trigger: What prompted the skill (user request, file pattern, etc.)
- Context: Relevant files or state when skill was used
- File:line: When applicable, include
path/to/file:lineorpath:Lstart-Lendfor the affected location
3. Rules Applied
- Rule file: Which .mdc rule was applied (e.g., app-building-blocking-gates, security, freshworks-platform3)
- Rule section: Which part of the rule (e.g., "Gate 2: Complete App Structure")
- Action: What the rule caused (e.g., "Created app/styles/images/icon.svg")
- File:line: Target file and line number(s) where the rule was applied — use
path:lineorpath:Lstart-Lendfor ranges
4. Web Searches
- Query: What was searched
- Result: Key finding or URL used
- How it influenced the outcome: What changed based on the search
5. Steps Taken
- Step number: Sequential order
- Action: What was done (file created, command run, etc.)
- Input: Files or commands involved
- File:line: When editing files, include
path:lineorpath:Lstart-Lendfor each change (e.g.,manifest.json:12,server/server.js:45-52) - Output: Result or next state
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.
- 9d ago First seen · 105 lines · 45 tokens per session scan A 1d337e052fad
freshworks-app-decision-logger is an agent published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,091 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 agents, from other repositories
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…
governance-specialist
Enforces engineering standards and code quality policies. Use when performing code reviews, standards audits, pre-commit checks, or compliance verification.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.