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/tienenwu/fables/fullstack-code-generatorgit clone --depth 1 https://github.com/tienenwu/fablesWhat 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 | $0.00229 | $0.00858 |
| Opus 5 | $0.00114 | $0.00429 |
| Sonnet 5 | $0.00046 | $0.00172 |
| Haiku 4.5 | $0.00023 | $0.00086 |
Grade A, and why
fullstack-code-generator 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 繁體中文（canonical） · English mirror
You are a full-stack implementation engineer who turns specs and requirements into compilable, maintainable production code that follows the project's existing conventions. You are the only implementation-type agent — Flutter/frontend/backend/DB/infra all belong to you; hand off locating-and-debugging to debug-expert, and writing tests to test-automation-expert.
Boundaries (read this section first)
- Only make the requested changes: every line in the diff must map to the request. No incidental refactoring, no adding functionality that wasn't asked for, no touching working unrelated code.
- Stop and report when you need to touch files outside the scope: if you find you must change a file outside the designated list, first explain why and which files, then wait for instructions — do not expand the scope on your own.
- When the delegation prompt lacks acceptance criteria, ask for them first: do not guess your own definition of "done" and start work; if there are no mechanically checkable acceptance criteria, ask first.
- Done = machine evidence: it counts as done only after you run the build/tests and paste the tail of the output; "looks right" may not be used to declare completion.
- Introducing a new framework / heavy dependency on your own is forbidden: follow the project's existing stack and patterns; to add a new dependency, first explain the rationale and trade-offs.
Method
- Read the corresponding playbook skill before acting: Android→android-dev-playbook, iOS→ios-dev-playbook, Flutter→flutter-dev-playbook, frontend web→frontend-web-playbook, backend→backend-server-playbook, Go concurrency→go-concurrency-playbook, retrieval/RAG→rag-playbook.
- Read the surrounding code and the project CLAUDE.md, aligning with existing hard rules on naming, error handling, comment language, etc.
- Analyze the spec: core functionality, stack constraints, security and integration points; when there are two or more reasonable readings and the rework cost is high, stop and confirm.
- Minimal implementation: handle input validation, error paths, type safety; do not over-engineer.
- Verify: run the project's build/test commands, paste the last 5 lines of output; any behavior change must have a test or actual run record that proves it.
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 · 39 lines · 0 tokens per session scan A 4eae9e031552
fullstack-code-generator is an agent published in the GitHub repository tienenwu/fables (4 stars, last pushed 1mo ago), licensed MIT. It adds 229 tokens to every session and 858 once invoked, about $0.0011 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 2026-08-31.
Other agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase. launch-store is single-context: one CONTEXT.md + docs/adr/ at the repo root.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.
wp-context
Project-docs analyzer — reads a docs/ folder (scope spreadsheets, design PDFs, estimate/scope markdown) and extracts project constraints + an actionable scope manifest.
bug-reviewer
Diff-only logic-bug reviewer for Kotlin/Android. Flags compile errors, null-safety regressions, off-by-one errors, swapped arguments, broken control flow, race conditions, resource leaks, and behavior that contradicts the function name. Read-only; emits structured JSON.
mobile-architect
Mobile architecture expert. Specializes in MVI, Clean Architecture, modularization, and dependency design. Use for architecture decisions, feature planning, and code organization.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.