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 skills/qinghaoliqaq/autocoder/fullstack_devnpx skills add qinghaoliqaq/AutoCoder --skill fullstack_devgit clone --depth 1 https://github.com/qinghaoliqaq/AutoCoderWhat 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 | $0.00044 | $0.00547 |
| Opus 5 | $0.00022 | $0.00273 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
fullstack-dev 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fullstack Dev
This skill is a compact execution guide for API-backed feature work.
When To Use
Use this skill when the current subtask requires both sides of the system:
- adding or updating an API endpoint and the UI that consumes it
- implementing authentication, authorization, or session-dependent features
- shipping CRUD flows that span schema, handlers, client calls, and UI states
- wiring file upload, background processing, or realtime updates into the product
Core Rules
- Read the existing code paths end to end before editing.
- Keep the scope anchored to the current subtask; do not expand into a full rewrite.
- Prefer existing architectural patterns over introducing a second style.
- Make backend and frontend contracts explicit in code, not implied in prose.
- If a migration, config change, or dependency is required, apply the minimal robust change.
Backend Standards
- Validate input at the boundary.
- Return consistent success and error shapes.
- Do not hide failures with overly broad catch blocks.
- Keep business logic out of transport-layer glue where the project already separates them.
- Preserve auth and permission checks on every protected path.
Frontend Standards
- Reflect backend validation and auth states in the UI.
- Handle loading, empty, success, and error states explicitly.
- Do not assume stale cached data is correct after a write; refresh or reconcile it.
- Keep form state, optimistic updates, and retries understandable and bounded.
Integration Checklist
- Confirm route or handler registration.
- Confirm request payload and response shape.
- Confirm the client call site and state update path.
- Confirm in-scope permission behavior.
- Confirm not-found, invalid-input, and duplicate/conflict behavior where relevant.
Review Bar
The subtask is only ready for review when:
- the feature works across the backend/frontend boundary
- validation and error handling are present on both sides where needed
- auth and access control remain correct
- the implementation is integrated into the actual user flow, not left orphaned
- touched files are limited to what the subtask really needs
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 · 70 lines · 44 tokens per session scan A c531a34db2a8
fullstack-dev is a skill published in the GitHub repository qinghaoliqaq/AutoCoder (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 547 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 skills, from other repositories
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the exec tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败'…
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
email-draft
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a pre-send self-check.