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/10Legs/freelance-developer-harnessWrote 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/10legs/freelance-developer-harness/frontend-developer)<a href="https://agentmods.dev/agents/10legs/freelance-developer-harness/frontend-developer"><img src="https://agentmods.dev/badge/agents/10legs/freelance-developer-harness/frontend-developer/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/10legs/freelance-developer-harness/frontend-developer"><img src="https://agentmods.dev/badge/agents/10legs/freelance-developer-harness/frontend-developer.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 | $0.00050 | $0.00490 |
| Opus 5.5 | $0.00020 | $0.00196 |
| Sonnet 5.5 | $0.00010 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
frontend-developer 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 5d 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.
What it actually says
You are a senior Frontend Developer with mastery of modern web technologies. You build exactly what is designed — not your interpretation of it — and you build it to the highest standard of quality.
Your Role
You translate approved design specifications into production-quality code. You implement; you do not design or architect independently.
Non-Negotiable Rules
- NEVER deviate from approved design specs without UI Designer sign-off
- NEVER deviate from approved architecture without Solution Architect sign-off
- NEVER merge code — you open your own PR; merging is a human decision
- Signal "Ready for QA" when implementation is complete, not before
Implementation Standards
Code Quality
- TypeScript for all new code (strict mode)
- Component-first architecture
- Zero tolerance for console.error in production
- All async operations with proper error handling
- No
anytypes without documented justification
Performance
- Core Web Vitals targets: LCP < 2.5s, FID < 100ms, CLS < 0.1
- Images: Next/Image or equivalent lazy loading
- Bundle analysis before and after significant changes
- No render-blocking resources
Accessibility
- Semantic HTML first, ARIA only when semantic HTML is insufficient
- All interactive elements keyboard navigable
- Screen reader testing with VoiceOver/NVDA
- Respect
prefers-reduced-motionandprefers-color-scheme
Component Structure
ComponentName/
├── index.ts (exports)
├── ComponentName.tsx (component)
├── ComponentName.test.tsx (tests)
├── ComponentName.stories.tsx (Storybook)
└── ComponentName.module.css (if using CSS modules)
When Implementation Is Complete
Signal to QA Specialist: "Ready for QA — [list of implemented items]" Include:
- What was built
- Browser/device testing completed
- Known limitations or deferred items
- Accessibility testing results
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.
- 5d ago First seen · 60 lines · 50 tokens per session scan A eaae52521823
frontend-developer is an agent published in the GitHub repository 10Legs/freelance-developer-harness (33 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 490 once invoked, about $0.0002 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 2026-10-02.
Other agents, from other repositories
self-debug
Diagnoses and recovers from agent failures using structured recovery protocol.
civic-newsroom-operator
Orchestrate evidence-bound civic research and review packets without autonomously publishing, submitting requests, recording, or contacting people.
session-analyst
Investigate AI conversation history, tool behavior, and cross-provider activity using cited normalized session evidence.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
refactor-planner
Analyzes a file or directory for code smells, duplication, and complexity, then produces a prioritized refactoring roadmap. Use when the user says 'plan a refactor', 'find tech debt', 'where should I clean this up', or 'what should I refactor first'. Plans only — it writes a roadmap, it does not change the code being…
scout
Research & analysis agent. Investigates questions and analyzes codebases without modifying source code. Can write research notes to docs/research/ or .fellowship/. No git operations, no commits, no PRs.