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/sgaabdu4/hard-eng/codebase-designnpx skills add sgaabdu4/hard-eng --skill codebase-designgit clone --depth 1 https://github.com/sgaabdu4/hard-engWhat 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 | $0.00024 | $0.00325 |
| Opus 5 | $0.00012 | $0.00162 |
| Sonnet 5 | $0.00005 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
codebase-design 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
Codebase Design
Contract
- Input = accepted behavior + verified topology + current owners/callers.
- Goal = small public surface hides meaningful policy, state, ordering, errors, and dependencies.
- Prefer delete concept → move behavior to owner → deepen owner → add boundary only for a proven gap.
- One pass-through call, naming-only wrapper, speculative mode, or hypothetical seam ≠ abstraction.
- New product behavior/architecture decision →
he; this skill supplies structural evidence only.
Route
| Need | Load | Complete |
|---|---|---|
| Owner/module/API/wrapper/seam design or review | workflow.md | Current leak + proposed contract + deletion + blast radius + proof |
| Chosen boundary needs materially different interface options | alternatives.md | Compared options + recommendation + user decision/blocker |
Ownership
- Topology/callers/impact = Codebase Memory + native verification.
- Branch/PR/WIP verdict =
code-review; structural result = evidence input. - Public-behavior test design =
test-quality. - Commands/gates =
deterministic-checks.
Complete
- One canonical owner + explicit public contract + hidden caller knowledge.
- Direct callers + cross-package/data/schema/key/route/test/doc/config effects covered.
- Proposed structure deletes or concentrates complexity; moving/wrapping it = incomplete.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 35 lines · 24 tokens per session scan A bdf2ce46cba4
codebase-design is a skill published in the GitHub repository sgaabdu4/hard-eng (5 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 325 once invoked, about $0.0001 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
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-collective-intelligence-coordinator
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator.
agent-payments
Agent skill for payments - invoke with $agent-payments.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-shared-state
Share structured, evolving state between an AG-UI agent and its client with the AG-UI .NET SDK — the client seeds state on the request, the server reads it, mutates it, and streams the updated state back as snapshots or deltas alongside the chat. USE FOR: sending initial/working state from the client via…