A review that looks for unnecessary complexity in existing or proposed source code, tests, configuration, dependencies, plans, or architecture. It considers whether added structure is justified while preserving important safety, compatibility, and operational needs.

Use it to simplify or audit a design, implementation, test suite, dependency choice, configuration, architecture, or recommendation that may add unnecessary complexity.

It helps prevent over-engineered solutions and identifies maintenance burdens before they spread. It keeps complexity concerns separate from ordinary defect or security findings.

decomplex — Skill by maxedapps

Install

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.

agentmods

npx agentmods add skills/maxedapps/agent-skills/decomplex

Any agent

npx skills add maxedapps/agent-skills --skill decomplex

Clone the repo

git clone --depth 1 https://github.com/maxedapps/agent-skills

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 870 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00093	$0.00870
Opus 5	$0.00046	$0.00435
Sonnet 5	$0.00019	$0.00174
Haiku 4.5	$0.00009	$0.00087

Measured 2d ago against content hash 8e6492ce0297, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decomplex 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.

skills/decomplex/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decomplex

Hard rules

Exactly one mode:
- Prevention — unimplemented plans/designs/deps/safeguards
- Audit — existing source/tests/config/deps/architecture
- Finding triage — supplied recs that may add complexity
Fix before reviewing:
- target
- authority
- required behavior
- scope
Ask only when ambiguity changes those.
Targets immutable.
Only write: one .reviews/<slug>-decomplex.md.
Never edit reviewed artifacts (even if asked to fix).
Direct invoke and report not writable → stop.
- no chat-only substitute
- embedders may use their own fallback
- must not claim decomplex ran
Complexity trade-offs only.
Route defects/security/perf/plan-compliance to the owning workflow (e.g. code-review).
Simplicity ≠ fewer lines/helpers/deps.
Preserve evidenced:
- trust boundaries
- invariants
- compatibility
- lifecycle cleanup
- ops needs
Findings are advisory.
Consumer dispositions/implements/escalates.
“No potential complexity findings” is valid.
Consumers must:
- disposition every item
- never auto-implement
- ask user when in doubt

Admission gate (all required)

Concrete conceptual, maintenance, or operational burden
Absent/insufficient justification for current need
Realistic, reachable practical cost
Smallest concrete simpler alternative
Required behavior preserved
Proportionate value after simplification + regression cost
Explicit exception/boundary check

Evidence:

Confirmed or Supported only

If the gate fails:

bounded validation
user question
or omit

Never find on:

helper count
duplication alone
novelty
hypothetical scale
style alone

Prefer:

delete
direct use
local logic/helper
existing shared abstraction
new abstraction

Sequence

Contract
- mode
- target
- authority
- scope
- behavior
- report path
- constraints
- inspect callers/tests/config/history only as needed for the gate
Before candidates
- read references/complexity-gates.md fully
- contextual signals, not a quota checklist
Evaluate
- full gate each candidate
- order by expected simplification value
Recommend
- only: Act | Validate | Ask user
- do not perform the action
- triage mode: preserve every supplied ID
- triage dispositions: Act | Validate | Ask user | No action
Before write
- read assets/decomplex-review-template.md fully
- write exactly one report
- strip template guidance/empty sections
- keep inspected/skipped coverage + limitations
Verify
- report exists
- admitted items pass gate
- all triage IDs accounted
- no target file changed

Read the full file on GitHub · 126 lines

Files

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.

Changes

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 · 126 lines · 93 tokens per session scan A 8e6492ce0297

Subscribe to this mod's changes

decomplex is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 18d ago), licensed MIT. It adds 93 tokens to every session and 870 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 2026-08-30.

Code review

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens