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/igorwarzocha/howaboua-pi-stuff/codebase-hygienenpx skills add IgorWarzocha/howaboua-pi-stuff --skill codebase-hygienegit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/codebase-hygiene)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/codebase-hygiene"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/codebase-hygiene.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 | $0.00015 | $0.01239 |
| Opus 5 | $0.00008 | $0.00620 |
| Sonnet 5 | $0.00003 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
codebase-hygiene 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load applicable rules
Loaded references are authoritative.
- Structural movement, ownership migration, and compatibility cleanup:
references/refactoring.md - Test assessment, addition, deletion, and scoring:
references/testing.md - Calls, dispatch, callbacks, continuations, imports, initialization, startup, and runtime cost:
references/execution-topology.md - Dependencies, lockfiles, installers, scripts, CI actions, runtimes, compilers, and third-party tools:
references/dependency-safety.md - Load every reference matching a repository language:
references/js-ts.md,references/python.md,references/go.md,references/rust.md - React components, Hooks, rendering, state, and framework boundaries:
references/react.md - For other languages, use repository evidence and current official ecosystem documentation.
- Scores and caps:
references/scoring-rubric.md. Score only when requested or already required.
Goal: leave a codebase that another agent can navigate efficiently, change coherently, verify quickly, and explain to a human from the code itself.
Inspect before editing
Optimize for agents working through search, bounded reads, and coherent multi-file edits. Do not imitate one-file-at-a-time human editing.
Read governing instructions, owning files, consumers, contracts, tests, active checks, runtime edges, and generated or framework-owned areas. Read every file you will change in full, continuing through tool chunks when needed. Search confirms callers and edges but does not replace understanding the owner.
Shape ownership
- Resist append bias. Before adding a branch, field, handler, test, or helper, decide whether it strengthens the current owner or reveals another responsibility.
- Exclude generated, vendored, and framework-owned files from size judgment unless maintained directly.
- Treat a maintained file above roughly 300 lines as a godfile candidate, not an automatic failure. Inspect mixed concerns, unrelated change reasons, central-path growth, hidden state, and agent readability. Cohesive stable tables, protocols, and algorithms may remain large. Growing mixed-responsibility files may not.
- Treat a function above roughly 50 lines as a review candidate. Split across ownership, abstraction level, state transition, effect, or failure-policy boundaries. Keep coherent algorithms and state machines together when extraction hides ordering.
- Collapse one-use helpers, wrapper factories, interfaces, and microfiles that add navigation without owning a decision, contract, translation, effect, lifecycle, resilience, security, or diagnostic boundary.
What ships with it
10 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.
- references/dependency-safety.md 2.6 KB
- references/execution-topology.md 3.0 KB
- references/go.md 3.0 KB
- references/js-ts.md 2.9 KB
- references/python.md 2.8 KB
- references/react.md 3.6 KB
- references/refactoring.md 3.8 KB
- references/rust.md 2.7 KB
- references/scoring-rubric.md 4.6 KB
- references/testing.md 3.0 KB
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 Changed · +1 lines 294c4771e6ef
- 5d ago First seen · 76 lines · 15 tokens per session scan A 9b96f3af3a73
codebase-hygiene is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (346 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,239 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
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…