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/yeaight7/agent-powerups/architecture-simplificationnpx skills add yeaight7/agent-powerups --skill architecture-simplificationgit clone --depth 1 https://github.com/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/architecture-simplification)<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/architecture-simplification"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/architecture-simplification.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 | $0.00031 | $0.00523 |
| Opus 5 | $0.00015 | $0.00262 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
architecture-simplification 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Over time, codebases accumulate "just in case" abstractions. This skill guides the safe removal of unnecessary complexity: remove the noise around the core logic without changing the core logic itself.
When to Use
- An interface has only one implementation and no second one is planned
- A wrapper, factory, or layer only passes arguments straight through
- Two code paths do the same thing and should be consolidated
Inputs
- The suspect abstraction(s) and their call sites
- A green test suite covering the affected area
Workflow
-
Identify the abstraction cost. Does this interface have only one implementation? Does this wrapper class just pass arguments straight through? Measure before cutting:
grep -rn "implements IUserRepository" src/ # count implementations grep -rn "IUserRepository" src/ | wc -l # count references -
Run the tests first. The affected area must be green before any removal — this is the behavioral baseline.
-
Inline the logic. Move the logic from the unnecessary abstraction directly into the caller.
-
Delete the dead code. Remove the interface, wrapper, or factory that is no longer needed.
-
Test verification. Re-run the same tests; the observable behavior of the system must not have changed.
Example: if a UserRepository implements IUserRepository but there is only ever one database, inline UserRepository and delete IUserRepository.
Output
- The simplified code with the abstraction removed
- Before/after test evidence showing unchanged behavior
Verification
- Tests covering the area were green before the change (baseline)
- Same tests green after the change — observable behavior preserved
- No references to the removed abstraction remain (searched, not assumed)
- Diff contains only removal/inlining — no core-logic rewrites
Failure Modes
- Rewrite disguised as simplification — do not rewrite the entire subsystem; simplification removes the noise around the core logic, not the logic itself.
- Cutting without a baseline — without a green pre-change test run, "tests pass after" proves nothing.
- Speculative retention — keeping the interface "in case we need it later" recreates the original problem.
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.
- 5d ago First seen · 57 lines · 31 tokens per session scan A 6ee9efda8da5
architecture-simplification is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 523 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
spike
Throwaway experiments to validate an idea before build.