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 instructions/vaquarkhan/fullstack-development-agent-skills/agents-mdgit clone --depth 1 https://github.com/vaquarkhan/Fullstack-development-agent-skillsWrote 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/instructions/vaquarkhan/fullstack-development-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/vaquarkhan/fullstack-development-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vaquarkhan/fullstack-development-agent-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.00520 | $0.00520 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
Fullstack-development-agent-skills AGENTS.md 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 3d 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
Fullstack Agent Skills
Open skill registry for fullstack delivery — 117 skills (72 core + 45 stack packs), 15 presets, 20 starter packs.
Start Here
- Read
skills/using-fullstack-agent-skills/SKILL.md - Select one preset from
presets/(stack defaults) - For deep implementation work, load skills from
skill-packs/(Java, Python, Go, PHP, Ruby) - Follow lifecycle commands in
.cursor/commands/or.claude/commands/ - Choose a starter pack from
starter-packs/for problem-area bundles
Core Lifecycle
/specdefine scope and contracts/plancreate safe implementation slices/buildimplement frontend and backend changes/validateprove quality and compatibility/reviewrun frontend, reliability, and security lenses/shiprelease with staged rollout and rollback triggers/migratezero-downtime schema and platform migrations/hardensecurity, reliability, and performance hardening/incidenttriage and runbook execution/optimizeperformance, cost, and capacity
Key Directories
| Directory | Purpose |
|---|---|
skills/ |
72 cross-stack workflow skills (spec, ship, cloud, identity, patterns) |
skill-packs/ |
45 stack-specific skills (Spring Boot, NestJS, .NET, Rust, Flutter, AI SDKs, etc.) |
presets/ |
15 platform presets (React, Node, Java, AWS, Azure, GCP, K8s) |
starter-packs/ |
20 YAML bundles by use case (SaaS, payments, GitOps, chaos) |
references/ |
14 operational checklists with provenance footers |
examples/ |
10 architecture blueprints (README-only design packs) |
agents/ |
6 reviewer personas |
registry/assets.json |
Machine-readable index (v0.4.0) |
skills-index.md |
Human-readable catalog |
docs/fullstack-skills-catalog.md |
Full inventory and roadmap |
Validation
python scripts/validate-skills.py
python scripts/check-skill-boilerplate.py
python scripts/validate-assets.py
python scripts/run-skill-routing-benchmark.py
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.
- 3d ago First seen · 49 lines · 520 tokens per session scan A 995582a86dff
Fullstack-development-agent-skills AGENTS.md is an instructions file published in the GitHub repository vaquarkhan/Fullstack-development-agent-skills (2 stars, last pushed 18d ago), licensed MIT. It adds 520 tokens to every session, about $0.0026 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 instructions, from other repositories
apisix AGENTS.md
Instructions for apache/apisix, covering apache apisix — agent instructions and security model.
spartan CLAUDE.md
Instructions for spartan-ng/spartan, covering working in this repo (notes for claude / ai agents), before pushing: run the ci checks locally and pull requests.
openbridge-webcomponents watch-radial-instruments.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.
openbridge-webcomponents external-scale.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering external scale & bar/gauge components, architecture overview, core renderer architecture, thin wrapper pattern and fixed-config gauge pattern.
openbridge-webcomponents line-area-charts.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering line/area charts & gauge trend, architecture overview, key principle: logic in base class, subclasses stay thin, base class architecture and line graph (non-filled).
openbridge-webcomponents setpoint.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering setpoint system, architecture overview, when to use mixin vs bundle, setpointmixin usage and setpointbundle usage.