Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.
Borrowing it
Nothing to install: this file belongs to Jwuthri/Tracely-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jwuthri/Tracely-ai/master/.claude/skills/deslop/SKILL.mdgit clone --depth 1 https://github.com/Jwuthri/Tracely-aiWrote 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/jwuthri/tracely-ai/deslop)<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/deslop"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/deslop/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/jwuthri/tracely-ai/deslop"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/deslop.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 | $0.00163 | $0.01868 |
| Opus 5 | $0.00081 | $0.00934 |
| Sonnet 5 | $0.00033 | $0.00374 |
| Haiku 4.5 | $0.00016 | $0.00187 |
Grade A, and why
deslop 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 10d 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.
This is a copy
100% identical to deslop — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslop: Remove AI Writing Patterns from Prose
Strip predictable AI patterns from writing. Make prose sound like a specific human wrote it, not like a language model generated it.
When to Apply
- Any request to "make it sound human" or "deslop" writing
- Any prose (articles, blog posts, essays, memos, newsletters, reports) or scientific writing (manuscripts, abstracts, cover letters, grant narratives, discussion sections, peer review responses) where the user wants it to sound natural rather than AI-generated
- Editing or revising existing text where the user wants it to sound natural rather than AI-generated
- Reviewing text for AI tells
Core Rules
1. Cut filler phrases
Remove throat-clearing openers ("Here's the thing:"), emphasis crutches ("Let that sink in."), business jargon ("navigate the landscape"), and meta-commentary ("In this section, we'll explore..."). See references/phrases.md for the full catalog.
2. Break formulaic structures
Avoid binary contrasts ("Not X. Y."), negative listings ("Not a X. Not a Y. A Z."), dramatic fragmentation ("Speed. That's it. That's the tradeoff."), self-posed rhetorical questions ("The result? Devastating."), and anaphora/tricolon abuse. See references/structures.md for patterns and fixes.
3. Eliminate AI tropes
Watch for the full catalog of AI writing tells: "quietly" and other magic adverbs, "delve" and its cousins, the "serves as" dodge, false ranges ("from X to Y" where the range is meaningless), superficial participle analyses ("highlighting its importance"), invented concept labels ("the supervision paradox"), grandiose stakes inflation, patronizing analogies, and false vulnerability. See references/tropes.md for the complete list with examples.
4. Use active voice with human subjects
Prefer active constructions with named actors. "The complaint becomes a fix" is wrong. "The team fixed it" is right. If no specific person fits, use "we" in scientific prose or "you" in blog posts.
What ships with it
6 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.
- 10d ago First seen · 134 lines · 163 tokens per session scan A 29d9ef462029
deslop is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,221 stars, last pushed today), licensed MIT. It adds 163 tokens to every session and 1,868 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deslop, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
Prompt Version Control Workflow
Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.
llm-tester
You are the LLM Tester, specializing in systematic prompt evaluation, red-teaming, and LLM output quality assurance. You replace "vibes-based" AI evaluation with rigorous, automated, and repeatable verification suites.
report-publisher
Publish an already validated report to an external release destination.
report-repair
Repair invalid local report.json files by inserting required report fields.
local-validator
Validate a local report.json file with a deterministic check-only script and no network access.
artifact-publisher
Validate and publish report artifacts to a remote release endpoint.