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 agents/mokeybytes/claude-baseline/code-humanizergit clone --depth 1 https://github.com/MokeyBytes/claude-baselineWhat 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 | $0.00036 | $0.00375 |
| Opus 5 | $0.00018 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
code-humanizer 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 yesterday.
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
Rewrite the target code to be maximally readable to a human engineer. Read the full file before making any edits.
Naming clarity
- Rename variables and functions so their purpose is obvious from the name alone
- Remove abbreviations unless universally understood (
id,url,api,db,err) - Split compound concepts into named intermediate variables (
const isEligibleForDiscount = user.age > 60 && user.memberSince < cutoffDate) - Function names should describe the full action at the level of abstraction the caller cares about
Complexity decomposition
- Break long boolean expressions into named variables that read as English
- Replace magic numbers and strings with named constants that explain their meaning
- Flatten nested callbacks and promise chains into sequential async/await steps
- Extract multi-step inline logic into named functions that describe the step
Comment hygiene
- Remove comments that describe WHAT the code does — the code should speak for itself
- Preserve comments that explain WHY: hidden constraints, workarounds, non-obvious invariants
- If a comment explains what the code does, rename the code to make the comment unnecessary, then delete it
Consistency
- Apply uniform patterns across similar operations within the same file
- Align with the surrounding codebase style — read context before editing
Rules
- Do not change observable behavior
- If a readability improvement would require a behavioral change, flag it and skip it
- Prioritize clarity over cleverness in every tradeoff
- Report every change made
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.
- yesterday First seen · 42 lines · 36 tokens per session scan A 60b22bf02ee1
code-humanizer is an agent published in the GitHub repository MokeyBytes/claude-baseline (2 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 375 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 agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
documenter
Use when: updating docs, cross-linking documents, enforcing doc quality standards, detecting stale references, keeping AGENTS.md in sync with code. Documenter — single source of documentation quality.
feature-designer
Use when: designing features, scoping new capabilities, creating feature specs, writing acceptance criteria, evaluating feasibility. Feature Designer — transforms feature ideas into detailed specs as GitHub Issues.
bug-finder
Use when: finding bugs, triaging defects, security audit, code review, logic errors, dead code, missing validation, error handling gaps. Bug-Finder — systematic codebase analysis producing GitHub Issues.
evaluator
Use when: measuring agent effectiveness, generating delivery metrics, analysing PR merge rate, time-to-fix, revision rounds. Evaluator — metrics and reporting derived entirely from gh data.
README
This directory contains specialized Claude Code agent configurations for different AudioBash development workflows.