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 skills add wsauret/flywheel --skill flywheel-conventionsgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/flywheel-conventions)<a href="https://agentmods.dev/skills/wsauret/flywheel/flywheel-conventions"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/flywheel-conventions.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 5.1 | $0.00022 | $0.01976 |
| Opus 5 | $0.00011 | $0.00988 |
| Sonnet 5 | $0.00004 | $0.00395 |
| Haiku 4.5 | $0.00002 | $0.00198 |
Grade A, and why
flywheel-conventions 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 8d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elegance — applied at every stage
Maximize elegance. This is the single governing principle. Every rule below describes what elegance looks like — heuristics in service of the principle, not the goal themselves. When a rule produces awkward or indirect output, break it and document why the result is more elegant.
Maximize elegance over minimizing churn. Pick the more elegant design no matter how big the refactor. Better now than months from now with more features and dependencies in place.
The output — plan or code — must read as if every decision was deliberate. A reader should never ask "why is this here?" about any line, phase, or task.
Decision checklist (heuristics, not laws — interrogate any check that feels wrong)
| # | Check | If violated |
|---|---|---|
| 1 | Is there exactly one source of truth for this data? | You're creating a copy. Read from the existing source. |
| 2 | Would deleting this code change behavior? | If not, delete it now. |
| 3 | Is this abstraction used in 2+ places? | If not, inline it — unless inlining would force the caller to do two unrelated jobs. |
| 4 | Does this wrapper add a new capability? | If not, call the underlying API directly. |
| 5 | Could a reader understand this in 30 seconds without context? | If not, the names or shape are wrong. |
| 6 | Does data flow in one direction? | If A updates B and B updates A, you have a cycle. Pick one owner. |
| 7 | Are you fighting the language or framework? | Use the idiomatic primitive. Ceremony signals the tool wants to be used differently. |
| 8 | Are you adding something speculative ("we might need…")? | Delete it. Add when the need is concrete. |
Anti-patterns and dispatch bar
For the canonical anti-pattern catalog and the elegance dispatch bar, see references/elegance.md. Use catalog names ("Shallow Wrapper", "Forwarding Chain", "Parallel State", "Premature Abstraction", "Dead Code", "God Class", and the Universal Principles) when leading the Failure paragraph in findings — plan-consolidation routes structural failures to redesign by these names.
What ships with it
2 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.
- 8d ago First seen · 165 lines · 22 tokens per session scan A 90bdf90229b2
flywheel-conventions is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 1,976 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
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
best-of-n
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.