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 ngocsangyem/MeowKit --skill simplifygit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/simplify)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/simplify"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/simplify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/simplify"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/simplify.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.00814 |
| Opus 5 | $0.00049 | $0.00407 |
| Sonnet 5 | $0.00020 | $0.00163 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
mk:simplify 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Simplification
Runs after implementation, before review. Reduces complexity while preserving behavior.
For ad-hoc quality review outside the current implementation diff, use
mk:clean-code.mk:simplifyis behavior-preserving and scoped to the current diff only.
Iron Rule
Behavior must not change. Every simplification must pass the exact same tests as before. If tests fail after simplification, the simplification was wrong — revert it.
What to Look For
Remove
- Dead code — functions never called, variables never read, unreachable branches, import never used
- Commented-out code — if it's in git history, delete it from source
- Unnecessary abstractions — wrapper that adds no value, interface with one implementation
- Redundant null checks — checking null after a guard that already prevents null
Simplify
- Deep nesting — 3+ levels of if/else → extract early returns or guard clauses
- God functions — >50 lines → extract focused helpers
- Duplicate logic — same pattern in 3+ places → extract shared utility
- Complex conditions —
if (a && !b || (c && d))→ extract to named boolean or function
Don't Touch
- Working code that's "not how I'd write it" — style is not complexity
- Performance-optimized code — it looks complex for a reason
- Code outside the current diff — scope discipline, even for simplification
Process
- Identify — scan changed files for complexity signals
- Propose — list each simplification with before/after preview
- Apply — make changes one at a time
- Verify — run full test suite after each change (not batched)
- Report — list what was simplified and why
Gotchas
- "Just one more cleanup" — scope creep is the #1 risk. Only simplify code from the current diff
- Removing "dead" code that's used via reflection/dynamic import — grep for string references, not just static imports
- Extracting too early — 2 copies is not enough to justify a shared utility. Wait for 3
- Breaking public API — simplifying internals is fine; changing exported signatures is a breaking change
- Test-only code — don't simplify test helpers/fixtures; they prioritize readability over DRY
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.
- 9d ago First seen · 82 lines · 99 tokens per session scan A e7fe3cfd37e2
mk:simplify is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 814 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.
deploy
Use when ready to ship — runs pre-push gates (lint, typecheck, build, tests, security sweep), commits, releases, and pushes. Standalone, never auto-invoked. Push always requires explicit confirmation. Trigger with /hyperflow:deploy, "ship it", "ready to push", "release", "cut a release", "deploy".
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
hyperflow-deploy
Hyperflow ship phase. Use when the user is ready to release — verbs like ship, push, release, deploy, "cut a release", "ready to push". Runs pre-push gates (lint + typecheck + build + tests + security sweep), then asks before pushing. Never --no-verify, never force-push to main.