avoid-ai-writing is a portable writing skill that detects common patterns associated with AI-generated prose and can rewrite them or make targeted edits to prose files. It is for users of Claude Code, OpenClaw, Hermes, and other compatible coding agents who want text to sound more like human writing. The catalogue entries are the skill's rule and instruction components.
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 skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing-routergit clone --depth 1 https://github.com/conorbronsdon/avoid-ai-writingWrote 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/conorbronsdon/avoid-ai-writing/avoid-ai-writing-router)<a href="https://agentmods.dev/skills/conorbronsdon/avoid-ai-writing/avoid-ai-writing-router"><img src="https://agentmods.dev/badge/skills/conorbronsdon/avoid-ai-writing/avoid-ai-writing-router/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/skills/conorbronsdon/avoid-ai-writing/avoid-ai-writing-router"><img src="https://agentmods.dev/badge/skills/conorbronsdon/avoid-ai-writing/avoid-ai-writing-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01270 |
| Opus 5 | $0.00020 | $0.00635 |
| Sonnet 5 | $0.00008 | $0.00254 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
avoid-ai-writing-router 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avoid AI Writing Router
Coordinate the public Skills as a bounded workflow. Route to the narrowest owner, preserve context between stages, and stop when the requested job is complete. This Skill does not replace the original avoid-ai-writing rulebook.
Authority chain
../avoid-ai-writing/SKILL.mdis the canonical editorial authority.references/handoff-contract.mddefines what context and evidence can cross Skill boundaries.references/skill-graph.jsonis the machine-readable source for nodes, typed edges, guards, and loop limits.references/routing-matrix.mdis the human-readable routing table.references/agency-role-lenses.mddefines the architecture, AI-evidence, implementation, and representation review lenses used to inspect the network.
Do not weaken, duplicate, or contradict the canonical Skill's preservation rules, evidence caveats, voice rules, pattern tiers, or pass behavior.
Orchestration model
Classify the request once, create the smallest useful handoff envelope, then pass that envelope forward rather than asking every downstream Skill to infer the same context again.
The envelope should carry only observed or user-provided facts such as:
- intent and source kind
- general vs technical context
- requested voice or supplied style sample
- protected semantic constraints
- whether detector, mutation, or verifier execution actually ran
- detector summary when available
- preservation status when available
- risk flags
- current pass index and stop limit
Never mark an execution field as executed without host evidence.
Primary routing
- Scan, detect, audit, score, or flag-only requests go to
ai-writing-detector. - Returned-text rewrite, humanize, clean-up, or remove-AI-isms requests go to
voice-preserving-rewriter. - A named file plus an explicit request to change that file goes to
file-edit-in-place. - Original plus rewrite, before/after comparison, or preservation validation goes to
preservation-verifier. - Claims about proving AI use, cheating, fraud, dishonesty, hiring suitability, or similar consequential conclusions go to
false-positive-reviewer. - Explicit invocation of the original Skill may remain in
avoid-ai-writingunless the request clearly needs a specialized stage.
What ships with it
7 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.
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 · 117 lines · 41 tokens per session scan A 4a3a88b0162f
avoid-ai-writing-router is a skill published in the GitHub repository conorbronsdon/avoid-ai-writing (4,244 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,270 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 2026-09-05.
Other skills, from other repositories
unmachined
Finds and removes AI slop from prose, UX copy, and web interfaces. Use when writing, auditing, or revising articles, posts, READMEs, marketing copy, UI copy, layouts, or frontend code that must not feel AI-generated; when the user says unmachined, de-slop, AI slop, anti-slop, humanize, make this human, sounds like AI…
compress
Prompt-Studio memory compressor. Shrinks CLAUDE.md, todo lists, and preference files into Prompt-Studio's lean format to cut input tokens on every load. Preserves all technical substance, code, URLs, and structure. Compressed output overwrites the original; human-readable backup stored out-of-tree as FILE.original.md…
lean-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes…
lean-gain
Show Lean's measured impact as a compact scoreboard: less code, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /lean-gain, "lean gain", "what does lean save", "show lean impact", "lean scoreboard".
lean-debt
Harvest every lean: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals Lean leaves behind get tracked instead of rotting into "later means never". Use when the user says "lean debt", "/lean-debt", "what did lean defer", "list the shortcuts", "lean ledger", or "what did we mark to do…
lean-help
Quick-reference card for all Lean modes, skills, and commands. One-shot display, not a persistent mode: shows the card and exits without switching levels, writing flag files, or persisting anything. Trigger: /lean-help, "lean help", "what lean commands", "how do I use lean", "lean cheatsheet", "lean reference".