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/jd-solanki/airig/code-organisationnpx skills add jd-solanki/airig --skill code-organisationgit clone --depth 1 https://github.com/jd-solanki/airigWrote 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/skills/jd-solanki/airig/code-organisation)<a href="https://agentmods.dev/skills/jd-solanki/airig/code-organisation"><img src="https://agentmods.dev/badge/skills/jd-solanki/airig/code-organisation.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 | $0.00078 | $0.01341 |
| Opus 5 | $0.00039 | $0.00671 |
| Sonnet 5 | $0.00016 | $0.00268 |
| Haiku 4.5 | $0.00008 | $0.00134 |
Grade A, and why
code-organisation 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code organisation
One principle sits under everything here: what changes together lives together. Co-locate code that changes for the same reason; separate code that changes for different reasons. Apply it at three zoom levels — system → module → file — each the same rule at a different scale.
This skill is reference. Read the level you are working at.
Placing new code
A short procedure for the recurring question "where does this go?":
- Name its reason to change in domain language — the feature or concept it serves. Done when you can finish "this changes when ___" without naming a technology.
- Find the home that shares that reason — the module whose other code changes on the same trigger. Done when you have checked siblings at the right zoom level, not only the file you are already in.
- Place it, or create a sibling. If a home fits, add it there; if none fits, create a new sibling at that zoom level, named for the concept. Done when the new code's neighbours are the things that change with it.
- Confirm the feature did not scatter — one logical change should not force edits across many directories. Done when a typical change to this feature stays inside one module.
System level — the repository
- Bounded context: split the system into self-contained models, each with its own consistent language — one context's
Accountneed not mean another's. Map the relationships between contexts explicitly instead of letting one model sprawl across the whole system. - Layered architecture: isolate the domain from UI, application, and infrastructure. Dependencies point inward; the domain layer holds the model and knows nothing of frameworks or persistence.
- Source tree is not the build tree: version-control inputs — source, scripts, fixtures — and never commit outputs — object files, binaries, coverage, generated docs. Build out-of-source so generated artifacts never pollute the source tree.
- Grow by component, not by accretion: a single source directory is fine until it isn't; as the project grows, divide into component directories rather than letting one directory swell.
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.
- 4d ago First seen · 59 lines · 78 tokens per session scan A c71d3b5527f8
code-organisation is a skill published in the GitHub repository jd-solanki/airig (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,341 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…