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/dtsola/xiaoyaosearch/code-simplifiergit clone --depth 1 https://github.com/dtsola/xiaoyaosearchWhat 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 | $0.00034 | $0.00587 |
| Opus 5 | $0.00017 | $0.00293 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
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 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 53 lines · 34 tokens per session scan A 2a51e8d21058
code-simplifier is an agent published in the GitHub repository dtsola/xiaoyaosearch (1,085 stars, last pushed 3mo ago), with no licence file. It adds 34 tokens to every session and 587 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 2026-08-30.
Other agents, from other repositories
writer
Writes ONE H2 section of a blog post given a section spec + research brief + style references. PHYSICALLY OFFLINE (no Bash, no WebFetch, no WebSearch in tool whitelist) — must use only the curated context provided. Spawned in parallel by phase-build section-drafter (N agents, one per H2).
editor-in-chief
Final reviewer of full assembled draft. Runs 12-item editorial checklist. The ONLY agent allowed to reverse-callback upstream (writer, humanizer, linker) for surgical fixes. Hard revision cap of 3 rounds before declaring done.
humanizer
Removes AI tells and applies voice + purpose calibration to existing draft. Edit for draft.md (preserves human edits), Write ONLY for humanizer-report.json output. Three modes: detect / rewrite / edit. Iterates max 3 times until AI-Slop score < 20.
publisher
Execute the 7-step WordPress publish flow with full rollback support. Reads workspace artifacts + invokes wppublisher.py + tracks every action in change-log.json (7-day undo window). Only agent allowed to call WP REST API mutations. NOT for refresh — use rewrite skill for refresh.
image-visual-qa
Vision QA for generated article images. Reads every PNG in images.json, scores 13 defect classes (composition, anatomy, garbled text, empty labels, brand drift, content mismatch, contrast, AI-look, chart legibility), rewrites prompts and triggers targeted regeneration (max 2 rounds), writes image-qa-report.json. Never…
reviewer
Independent reviewer with NO pipeline history. Reviews final draft as fresh editor (Google E-E-A-T + Perplexity citation judge). Outputs review.json with 0-100 score + 3 "would change". Reverses to repair-orchestrator if score < target. Quality Gate 4 of 4.