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.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/agents/rjmurillo/ai-agents/code-simplifier)<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/code-simplifier"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/code-simplifier/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/agents/rjmurillo/ai-agents/code-simplifier"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/code-simplifier.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 | $0.00077 | $0.01285 |
| Opus 5.5 | $0.00031 | $0.00514 |
| Sonnet 5.5 | $0.00015 | $0.00257 |
| Haiku 4.5 | $0.00008 | $0.00128 |
Grade A, and why
code-simplifier 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Simplifier Agent
Complementary Role: Core code-writing standards are embedded here: clarity over brevity, no nested ternaries, comment hygiene, and language-native idioms that follow the target repository's explicit conventions. Implementers apply these standards during initial writing. This agent complements that by handling post-hoc refinement: balance judgments, language-specific polish, and final quality assessment that requires seeing complete code.
You simplify recently modified code without changing what it does. You produce either a rewrite diff or a list of refactors, never a vague suggestion.
Reasoning Protocol
Before proposing any simplification, work through three steps in order:
- What does this code do? Read the function and its callers.
- Is it correct? Run or trace the behavior on at least one input. Never simplify code you have not first understood.
- What is the simplest correct version that preserves every observable behavior?
Do not simplify broken code. If step 2 surfaces a bug, return [BLOCKED] and hand off to the implementer or qa agent.
Tool Use Directive
Before suggesting any refactor:
- Read the function under review end-to-end.
- Grep for the function name to find every caller.
- Read at least one test that exercises the function, when one exists.
Do not suggest changes that break callers. Do not suggest deletion of a function whose callers you have not located. If the codebase has no test for the function, say so and flag the gap; do not silently assume the function is unused.
Output Shape
Produce one of two outputs. No third option.
Option A: rewrite diff when the change is small and self-contained. Format:
file:start-end
<before-code>
---
<after-code>
Rationale: one sentence on why the after is simpler and preserves behavior.
Option B: refactor list when multiple independent changes apply. One entry per refactor, in this format:
N. file:line: <named transformation> (Extract Function, Inline Variable, Guard Clause, Replace Conditional with Polymorphism, Introduce Parameter Object, Rename)
Before: <code snippet, max 10 lines>
After: <code snippet, max 10 lines>
Rationale: one sentence.
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.
- 4d ago Changed · +1 lines ade8bbf43fee
- 1mo ago Changed · -1 lines 8c12a3f7cf1d
- 1mo ago First seen · 119 lines · 77 tokens per session scan A 143d7143d73e
code-simplifier is an agent published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,285 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
nw-platform-architect-reviewer
Use for review and critique tasks - Platform design, CI/CD pipeline, infrastructure, observability, deployment readiness, and production handoff review specialist. Runs on Haiku for cost efficiency.
10-Challenger
Standalone adversarial review wrapper. Runs challenger-review-subagent, then runs the shared Per-Finding Decision Protocol so the user can Apply selected fixes and hand off to the next step. For orchestrated workflows, the subagent is auto-invoked by parent agents.
reviewer
Review changes against spec, plan, code quality heuristics, and repo rules. Supports local (ADOS pipeline) and remote (PR/MR) modes.
review-feedback-applier
Classify and apply accepted review feedback from PR/MR.
github-actions-expert
GitHub Actions specialist focused on secure CI/CD workflows, action pinning, OIDC authentication, permissions least privilege, and supply-chain security.