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/griffinwork40/agent-framework/simplifynpx skills add griffinwork40/agent-framework --skill simplifygit clone --depth 1 https://github.com/griffinwork40/agent-frameworkWhat 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 | $0.00076 | $0.01730 |
| Opus 5 | $0.00038 | $0.00865 |
| Sonnet 5 | $0.00015 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
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 2d 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.
This is a copy
95% identical to simplify — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-agent contract
/contract
Overview
/simplify is a discovery-and-prioritization skill, not a correctness auditor (that is /review's job) and not a blind executor (that is /refactor's job). It answers: what incidental complexity, duplication, and dead weight exists in this code, and what is safe to remove? Default mode is read-only: a ranked reduction plan is emitted but nothing is changed. Writes only happen when --apply is explicitly passed.
Scope is diff-bounded by default (git diff origin/main, or working-tree/HEAD if no remote). Pass --all for a whole-repo sweep (where duplication and dead-code analysis pay off most). Pass an explicit [target] path or PR reference to override both. Code with no test coverage is safe to analyze but must never be auto-applied — the skill surfaces that gap and recommends /simplify [target] --all after adding tests, or produces the plan and stops.
Argument parsing
| Argument | Effect |
|---|---|
| (none) | Scope = git diff origin/main (working-tree fallback) |
[target] |
Explicit path, glob, or PR ref |
--all |
Whole-repo sweep; excludes node_modules/, dist/, generated files |
--apply |
Opt-in write mode; default is read-only plan |
Parse arguments before dispatching Wave 1. Resolve scope to a concrete file list or diff stat and attach it to every sub-agent prompt.
Wave 1 — Parallel discovery (read-only)
Dispatch all four lenses simultaneously as research-agent sub-agents. All are strictly read-only — no writes, no installs that modify package.json. Optional tooling (jscpd, knip) is an accelerant only; degrade to grep/structural reasoning when absent or network-gated.
(a) Duplication / clone detection
Find exact and near-duplicate logic blocks across modules within scope. Optionally seed with:
npx jscpd <scope> --reporters json --silent
If jscpd is absent, use grep for literal repetition and structural reasoning for semantic clones. Output: clone clusters with file:line ranges, estimated token overlap, and a suggested extraction site.
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.
- 2d ago First seen · 125 lines · 76 tokens per session scan A ce720df16e81
simplify is a skill published in the GitHub repository griffinwork40/agent-framework (23 stars, last pushed 7d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,730 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to simplify, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…