filter-tells

filter-tells is a skill for Claude Code from petar-djukic/writing-skills. It costs 82 tokens per session (7,307 once invoked), scanned A, original, MIT.

A writing review tool that finds common patterns in AI-generated text and helps rewrite them into more natural prose.

In plain words
What is it for?
Use it to review drafts for word choice, sentence structure, repeated openings, reasoning leakage, and other detectable AI-writing patterns.
Why use it?
It helps remove formulaic wording and sentence patterns that can make writing sound machine-produced.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code; installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .agents/skills/filter-tells/scripts/md_paragraphs.py <file.md> [--json] [--coverage-only].

Good fit Use it to review drafts for word choice, sentence structure, repeated openings, reasoning leakage, and other detectable AI-writing patterns.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/petar-djukic/writing-skills
agentmods
npx agentmods add skills/petar-djukic/writing-skills/filter-tells

Made for: Claude Code.

Wrote 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.

agentmods badge for filter-tells

README.md
[![agentmods](https://agentmods.dev/badge/skills/petar-djukic/writing-skills/filter-tells/github.svg)](https://agentmods.dev/skills/petar-djukic/writing-skills/filter-tells)
Your own site
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/filter-tells"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/filter-tells/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.

agentmods 80×15 button for filter-tells

Your own site · 80×15
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/filter-tells"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/filter-tells.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.07307
Opus 5 $0.00041 $0.03653
Sonnet 5 $0.00016 $0.01461
Haiku 4.5 $0.00008 $0.00731

Measured 7d ago against content hash 5f77e2f65385, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

filter-tells 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 7d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (eval/run_eval.py, eval/test_run_eval.py, scripts/abstract-check.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/filter-tells/SKILL.md · 494 lines

How it starts

The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.

filter-tells: AI Writing Detection and Correction

Detects mechanically, removes editorially, and hands voice restoration to match-voice. Three detection layers — lexical, structural, semantic — flag passages; Claude then rewrites them under the convergence rules below, and re-scans. There is no deterministic strip: a banned word is a one-word swap, but a cadence tell needs the sentence rewritten, and that is judgment.

Filtering leaves prose that is neutral — no tells, but no voice either. When the passage has to sound like the author, that is match-voice's job.

Renamed from de-ai (2026-07). The old name implied the skill only removed; it detects, and the removal is editorial.

Standing Warning: Scripts Are Blind to Rhetorical Patterns

The two scripts (detect-lexical.sh, detect-structural.py) measure surface metrics only — banned words, opening diversity, sentence length variance, dash density. They cannot detect the rhetorical patterns that constitute most of the AI signal in real prose:

  • Declarative pairs ("X is Y. Z is W.")
  • Definition-by-enumeration ("X extends in two ways")
  • Meta-narrative bridges ("The analogy breaks in one place")
  • Triple parallels ("clearer instructions, tighter constraints, fewer ambiguous cases")
  • Comprehensive enumerated sweeps in parentheses

Partial exception: detect-structural.py now has a detect_antithesis check that catches the lexically-marked subset of negation-then-affirmation ("X is not Y. It is Z.", "The meter was.") and clipped antithesis fragments. It does not catch the purely semantic reversal ("Same quality out. Different bill." used without a negation word). Prompt 6 in Step 3 covers that remainder. Treat the regex as a recall aid, not full coverage of the pattern.

A clean or minor-issues verdict from the structural script means the surface checks passed. It does not mean the prose is in voice. Step 3 (semantic analysis by Opus) is the only layer that catches the rhetorical AI tells the scripts still miss. Skipping Step 3 produces false-negative reports.

Read the full file on GitHub · 494 lines

Files

What ships with it

37 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.

Changes

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.

  1. 7d ago Changed · +23 lines 5f77e2f65385
  2. 12d ago First seen · 471 lines · 82 tokens per session scan A 398038ce22c7

Subscribe to this mod's changes

filter-tells is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It adds 82 tokens to every session and 7,307 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

humanizer

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

NulightJens/humanizer-stack · 111 tokens

structural-humanizer

Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…

NulightJens/humanizer-stack · 188 tokens

story-import

A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.

zenstory-ai/oh-story-claudecode · 98 tokens

story-review

A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.

zenstory-ai/oh-story-claudecode · 74 tokens

story-long-analyze

A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.

zenstory-ai/oh-story-claudecode · 173 tokens

story-deslop

A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.

zenstory-ai/oh-story-claudecode · 62 tokens