unslop is agent-read markdown (skill) from firzus/agent-skills: Audit a codebase for dead code and AI slop, clear each suspect against the legitimate reason it exists, and remove only what the evidence carries..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Unslop
Find code that should not exist — **dead code** that no longer runs, and
**slop** that runs and earns nothing — then prove each candidate before
touching it. The product of a run is a ranked report with the evidence
attached; removal follows the user's approval, one deletion per commit.
## Two problems, two epistemics
Keep them apart at every stage. Auditing them in one pass is the error that
produces confident wrong deletions.
| | Dead code | Slop |
| --- | --- | --- |
| Question | Is this **reachable**? | Should this **exist in this form**? |
| Decided by | Reference graphs, call graphs, runtime evidence | Reading the code |
| Core | Decidable, with documented blind spots | No decidable core |
| Terminates in | A removal backed by evidence | A ranked report for a human |
**No tool decides deadness.** Each one decides a *decidable approximation* of
it, and the identity of that approximation — never the tool's confidence score
— determines whether removal is safe. Perfect detection reduces to the halting
problem, so every tool is either unsound for deletion or incomplete.
**Authorship is not the defect.** No detector of LLM-written source exists, and
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
A 17 of 17 checks passed. Deterministic, no model, same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (10715 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
firzus/agent-skills · 3 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_g6sbmn2xh2qyo2og
GET https://markdownregistry.com/api/v1/resolve?ref=firzus/agent-skills/unslop
GET https://markdownregistry.com/api/v1/blob/ad9d46930674c42b27f95439fe0eccd207d75dd7cdfe04f93251c69f6cf3daa0
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
firzus/agent-skills · skills/engineering/code-review/SKILL.md · Review a scoped diff against requirements, project standards, and correctness using independent read-only reviewers…
firzus/agent-skills · skills/engineering/deep-research/SKILL.md · Investigate a question across sources with delegated research, adversarial verification, and a reusable evidence…
firzus/agent-skills · skills/engineering/gamification/SKILL.md · Gamification design for products, apps, and game meta-layers: design an engagement, habit, or retention system; choose…
firzus/agent-skills · skills/engineering/implement/SKILL.md · Deliver prepared work with test-first verification, current documentation, and a verified handoff.
firzus/agent-skills · skills/engineering/interview/SKILL.md · Prepare approved Linear work briefs through a continuous interview, with progressive framing for large goals.
firzus/agent-skills · skills/engineering/prototype/SKILL.md · Resolve a bounded design or feasibility question through an observable experiment. Use for authorized interface, logic…
firzus/agent-skills · skills/engineering/security-review/SKILL.md · Perform source-only security audits of codebases, APIs, services, and applications. Use for security questions, focused…
parcha-ai/parcha-skills · unslop/skills/unslop/SKILL.md · Cut AI tells from text you write or edit for a human reader (commit messages, PR titles and bodies, docs, code…
j-star-films-studios/vibecode-protocol-suite · .agents/skills/unslop/SKILL.md · Use when writing any text, chat responses, documentation, UI copy, or skill instructions. Cuts AI tells, filler, and…
j-star-films-studios/vibecode-protocol-suite · assets/.agent/skills/unslop/SKILL.md · Use when writing any text, chat responses, documentation, UI copy, or skill instructions. Cuts AI tells, filler, and…
