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 agentmods add agents/ambient-code/platform/frontend-reviewgit clone --depth 1 https://github.com/ambient-code/platformWhat 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 | $0.00045 | $0.00749 |
| Opus 5 | $0.00023 | $0.00375 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
frontend-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 yesterday.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Review Agent
Review frontend code against documented conventions.
Context
Load these files before running checks:
specs/standards/frontend/conventions.spec.mdspecs/standards/frontend/react-query.spec.mdcomponents/frontend/DESIGN_GUIDELINES.md(if it exists)
Checks
F1: No raw HTML elements (Critical)
grep -rn "<button\|<input\|<select\|<dialog\|<textarea" components/frontend/src/ --include="*.tsx" | grep -v "components/ui/"
Must use Shadcn UI components from @/components/ui/.
F2: No manual fetch() in components (Critical)
grep -rn "fetch(" components/frontend/src/app/ components/frontend/src/components/ --include="*.tsx" --include="*.ts" | grep -v "src/app/api/"
Use React Query hooks from @/services/queries/.
F3: No interface declarations (Major)
grep -rn "^export interface \|^interface " components/frontend/src/ --include="*.ts" --include="*.tsx" | grep -v "node_modules"
Use type instead of interface.
F4: No any types (Critical)
grep -rn ": any\b\|as any\b\|<any>" components/frontend/src/ --include="*.ts" --include="*.tsx" | grep -v "node_modules\|\.d\.ts"
Use proper types, unknown, or generic constraints.
F5: Components under 200 lines (Minor)
find components/frontend/src/ -name "*.tsx" -print0 | xargs -0 wc -l | sort -rn | head -20
Flag components exceeding 200 lines. Consider splitting.
F6: Loading/error/empty states (Major)
For components using useQuery:
- Must reference
isLoadingorisPending - Must reference
error - Should handle empty data
grep -rl "useQuery\|useSessions\|useSession" \
components/frontend/src/app/ components/frontend/src/components/ --include="*.tsx"
Then check each file for isLoading\|isPending and error references.
F7: Single-use components in shared directories (Minor)
Check components/frontend/src/components/ for components imported only once. These should be co-located with their page in _components/.
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.
- yesterday First seen · 117 lines · 45 tokens per session scan A 024da8228180
frontend-review is an agent published in the GitHub repository ambient-code/platform (129 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 749 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 2026-08-30.
Other agents, from other repositories
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…