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 skills add freshworks-developers/fw-dev-tools --skill fw-reviewgit 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/skills/freshworks-developers/fw-dev-tools/fw-review)<a href="https://agentmods.dev/skills/freshworks-developers/fw-dev-tools/fw-review"><img src="https://agentmods.dev/badge/skills/freshworks-developers/fw-dev-tools/fw-review/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/skills/freshworks-developers/fw-dev-tools/fw-review"><img src="https://agentmods.dev/badge/skills/freshworks-developers/fw-dev-tools/fw-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 39 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 68 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00034 | $0.02508 |
| Opus 5.5 | $0.00014 | $0.01003 |
| Sonnet 5.5 | $0.00007 | $0.00502 |
| Haiku 4.5 | $0.00003 | $0.00251 |
Grade A, and why
fw-review 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 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.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entry contract
- Invoked by: controller after build/validate milestones or explicit review request
- Preconditions: App directory with
manifest.json;fdkavailable or user consented to fw-setup install - Returns:
done(review report emitted) |blocked(missing fdk / app dir) |escalate(unrecoverable manifest issues) - On complete: hand control back to the controller — controller offers publish; do not invoke fw-publish from this skill
- Session:
session-read.shat start; on pass —session-write.sh <app-dir> --merge-json '{"progress":{"milestones":["review_passed"],"phase":"review"}}' step=reviewed
fw-review
This is an automated pipeline. After the app directory is determined (Q1 pre-flight below), do not ask further questions or interact with the user for disambiguation — execute the remaining phases silently and produce only the formatted App Review Result block in rules/report.md. Do not prefix or suffix that block with commentary (no Pass/N/A rationales, script notes, or pipeline status).
Exception: If fdk is missing, follow FDK CLI availability below (STOP → offer /fw-setup-install → optional y/n) — that interaction overrides “silent only” until the CLI exists or the user declines install.
Pre-flight: determine app directory (Q1)
Before the workflow, follow the same steps as fw-app-dev /fdk-fix Step 1: Determine app directory:
- Search the workspace for
manifest.jsonfiles. - If multiple folders contain manifest.json: ask the user which app to review (this is the only user question allowed in this skill).
- If one folder: Use that directory.
- If none: Inform the user and stop.
All app files in the workflow below are relative to that directory (the folder containing manifest.json). Run deterministic check scripts from this skill’s scripts/ against <app-directory> (see README.md).
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 655 B
- .cursor-plugin/plugin.json 1.1 KB
- README.md 26 KB
- rules/frontend-files-rules.md 5.5 KB
- rules/iparam-rules.md 5.4 KB
- rules/report.md 12 KB
- rules/script-check-rules.md 4.3 KB
- scripts/common.js 542 B runs code
- scripts/external-import-sources.js 6.7 KB runs code
- scripts/fdk-errors-warnings.js 3.9 KB runs code
- scripts/freshworks-css-only.js 2.6 KB runs code
- scripts/https-imports.js 2.8 KB runs code
- scripts/image-resolution.js 3.1 KB runs code
- scripts/oauth-config-usage.js 3.3 KB runs code
- scripts/platform-version-upgrade.js 1.7 KB runs code
- scripts/unused-library-imports.js 2.9 KB runs code
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 Changed · +8 lines f66062c09021
- 1mo ago First seen · 103 lines · 34 tokens per session scan A dd1984ce2770
fw-review is a skill published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,508 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
battle-tested-engineer
Engineering judgment for code write/refactor/test and frontend UI. Trigger on code review, legacy cleanup, tests, UI with data, bloat/over-engineer complaints — even with no explicit mention, before any diff/rewrite/test suite. Output ultra-terse caveman style; code, commits, PR desc, security warnings stay normal…
refactor-with-ai
Use this skill when refactoring code with AI assistance. Activate when the user wants to improve code structure, extract functions, reduce complexity, modernize legacy code, apply design patterns, clean up technical debt, or restructure code while preserving behavior.
ai-code-reviewer
Use this skill when reviewing AI-generated code. Activate when the user has code generated by an AI assistant and wants to review it, validate AI output, check for common AI mistakes, ensure code quality of generated code, or verify that AI-generated code follows best practices before merging.
secure-code-review
Systematic security code review methodology. Use this skill when reviewing pull requests for security issues, auditing critical code paths, or performing security assessments. Activate when: security review, code audit, secure code, review PR for security, find vulnerabilities, security assessment.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.