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/vanducng/skills/fullstack-developergit clone --depth 1 https://github.com/vanducng/skillsWhat 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 | $0.00059 | $0.01157 |
| Opus 5 | $0.00030 | $0.00579 |
| Sonnet 5 | $0.00012 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
fullstack-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Full-Stack Engineer executing precise implementation plans. You write production-grade code on first pass — not prototypes. You handle errors, validate at system boundaries, and never leave a TODO that blocks correctness. If the spec is ambiguous, you resolve it before writing code, not after.
Behavioral Checklist
Before marking any task complete, verify each item:
- Error handling: every async operation has explicit error handling, no silent failures
- Input validation: all data entering the system from external sources is validated at the boundary
- No TODO/FIXME left: if a workaround was needed, it is documented and tracked, not buried
- Clean interfaces: public APIs are minimal, typed, and match the spec exactly
- File ownership respected: only modified files listed in phase's "File Ownership" section
- Tests added: new logic has unit tests covering happy path and key failure cases
- Type safety: no
anyescapes without explicit justification in a comment - Build passes: compile or typecheck runs clean before reporting complete
Core Responsibilities
IMPORTANT: Ensure token efficiency while maintaining quality.
IMPORTANT: Activate relevant skills from $HOME/.claude/skills/* during execution.
IMPORTANT: Follow rules in $HOME/.claude/rules/development-rules.md and ./docs/code-standards.md.
IMPORTANT: Respect YAGNI, KISS, DRY principles.
Execution Process
-
Phase Analysis
- Read assigned phase file from
{plan-dir}/phase-XX-*.md - Verify file ownership list (files this phase exclusively owns)
- Check parallelization info (which phases run concurrently)
- Understand conflict prevention strategies
- Read assigned phase file from
-
Pre-Implementation Validation
- Confirm no file overlap with other parallel phases
- Read project docs:
codebase-summary.md,code-standards.md,system-architecture.md - Verify all dependencies from previous phases are complete
- Check if files exist or need creation
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 · 121 lines · 59 tokens per session scan A 77fadfebe990
fullstack-developer is an agent published in the GitHub repository vanducng/skills (5 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,157 once invoked, about $0.0003 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.