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 magarcia/skills --skill simplifygit clone --depth 1 https://github.com/magarcia/skillsWrote 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/magarcia/skills/simplify)<a href="https://agentmods.dev/skills/magarcia/skills/simplify"><img src="https://agentmods.dev/badge/skills/magarcia/skills/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/magarcia/skills/simplify"><img src="https://agentmods.dev/badge/skills/magarcia/skills/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 | $0.00060 | $0.00477 |
| Opus 5.5 | $0.00024 | $0.00191 |
| Sonnet 5.5 | $0.00012 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
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 1mo 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
Simplify
Never change observable behavior. Report a real bug instead of hiding its fix inside cleanup, because a semantic change invalidates prior verification. Limit edits to the target diff and files that must change with it; do not perform drive-by refactors.
Read every changed file in full and every applicable AGENTS.md, then inspect:
- Reuse — Search for existing utilities, components, and types before adding another. Consolidate repeated code only when it represents the same concept and extraction reduces total complexity; two call sites alone do not justify an abstraction.
- Dead code — Remove unused imports, variables, branches, commented-out code, and debug logging introduced or exposed by the diff. Use configured project tooling such as Knip and linters when available. Do not add a dependency for this pass, and corroborate analyzer output against dynamic imports, generated code, exports, tests, and external consumers.
- Comments — Remove narration, stale history, and comments that merely restate code. Preserve intent, invariants, constraints, and non-obvious tradeoffs.
- Naming and structure — Ensure names describe current behavior and flatten avoidable nesting with early returns when clearer.
- Types — Remove unjustified
any, broad object types, and unchecked assertions or casts. Preserveunknownat untrusted boundaries and narrow or validate it immediately. Use configured cycle analysis when available; do not assume Madge is installed. - Efficiency — Remove accidental quadratic work and repeated parsing or fetching. Avoid speculative micro-optimization.
Run the smallest relevant tests, lint, typecheck, and diagnostics required by the repository and changed code. Summarize what changed, what was intentionally left alone, and any bugs reported.
- Prefer readable code over compact cleverness.
- Follow an established repository pattern even when another style is personally preferable.
- Leave unproven fallback, compatibility, and legacy-path removal out of scope. Suggest a separately scoped
$improve-vibecodeaudit when broader evidence-backed cleanup is warranted.
What ships with it
1 file 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.
- 1mo ago First seen · 24 lines · 60 tokens per session scan A ae3ec1194fed
simplify is a skill published in the GitHub repository magarcia/skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 477 once invoked, about $0.0002 per session on Opus 5.5. 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
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
receiving-code-review
A guide for handling code-review feedback carefully. Code review is the process of checking proposed changes before they are accepted into a project.
requesting-code-review
A code-review procedure for checking completed work against its requirements before it spreads or is merged. A code reviewer is a person or agent who looks for defects and missing parts.
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
rules-code-type-safety
The rules for the parameters, the properties and the return type of a signature. Use when you write a new method, a new function, a new class, a new constructor or a new property, when you add a parameter to a signature that exists, when you change what a method takes or what it returns, when you let a caller choose a…
rules-code-immutability
The rules for the state of an object. Use when you write a new class, a new struct or a new record, when you write a constructor, when you add a property to a type that exists, when you write a setter or a method that writes a property of its own object, when a caller needs an object with one different value, when a…