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/thuandiep1707/codex-harness-javascript/frontend-rulesgit clone --depth 1 https://github.com/thuandiep1707/codex-harness-javascriptWhat 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 | $0.00000 | $0.00478 |
| Opus 5 | $0.00000 | $0.00239 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
frontend-rules 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend rule architecture
Rule định nghĩa convention hoặc hành vi bắt buộc. Rule không phải workflow và không tự cấp authority để mở rộng scope.
Ownership
Coding specialist dùng:
.agents/specialists/coding/rules/component-decomposition-gate.md
.agents/rules/frontend-coding.md
.agents/rules/frontend/*.md
Testing specialist dùng .agents/rules/testing.md cùng local rule của chính nó. Brain, Orchestrator,
Design và Test Plan chỉ load rule được manifest của mình allow.
Frontend topic rules
| Topic | Trigger |
|---|---|
atomic-components.md |
Component placement, API, composition, variant |
icons-images-assets.md |
Icon, SVG, image, logo, marker, asset |
semantics-accessibility.md |
Interactive semantics, heading, form, ARIA, table |
styling-layout.md |
CSS, Tailwind, token, layout, responsive behavior |
react-state-runtime.md |
Server/client boundary, hook, state, provider, browser API |
async-states.md |
Loading, error, empty, permission, missing configuration |
generated-ui-validation.md |
Final validation for UI derived from design evidence |
Coding luôn load decomposition gate nhỏ. Gate chỉ load full atomic-components.md khi Subtask thật sự
đụng component/page/screen structure. Sau đó Coding chỉ load các topic rule khác khi trigger có trong
transient handoff hoặc source evidence. Không load toàn bộ topic rules cho mọi task.
Specialist context boundary
Frontend/testing rules không được dùng làm lý do để đọc .docs/. Requirement của specialist chỉ đến
từ transient issue-handoff và dependency evidence được Orchestrator cung cấp.
Nếu rule xung đột với handoff, specialist trả blocker. Specialist không tự sửa Jira, parent Task hoặc workflow scope.
Khi thêm rule
Chỉ tạo rule mới khi có trigger ổn định, nhiều quyết định liên quan và owner rõ ràng. Micro-rule nên được thêm vào topic hiện có, trừ khi cần một always-loaded gate ngắn để bảo vệ flow. Khi policy xuất hiện ở nhiều nơi, chọn một normative owner và dùng cross-reference ngắn ở nơi còn lại.
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.
- 2d ago First seen · 48 lines · 0 tokens per session scan A b16390ae7c0d
frontend-rules is an agent published in the GitHub repository thuandiep1707/codex-harness-javascript (7 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 478 tokens. 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
independent-reviewer
Fresh-context read-only independent reviewer for SPEC-based acceptance evidence and integration recommendation.
task-specialist
Bounded implementer for one ready task with an exclusive write set and approved context.
discovery-interviewer
Read-only interviewer for missing, stale, or mature-project context before implementation planning.
learning-assessor
Read-only project-learning assessor used only after explicit learning activation and observation consent.
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.