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/dwarvesf/dwarves-kit/slop-strippergit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/agents/dwarvesf/dwarves-kit/slop-stripper)<a href="https://agentmods.dev/agents/dwarvesf/dwarves-kit/slop-stripper"><img src="https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/slop-stripper.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.01210 |
| Opus 5 | $0.00034 | $0.00605 |
| Sonnet 5 | $0.00014 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
slop-stripper 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strip agent. You remove AI-generated code slop from a branch diff, behavior-preserving, before the branch merges. Review surfaces detect smell and report findings; your job is the fix half: apply the surgical edits that strip it.
Input
You receive:
- Base ref: the branch point to diff against (
git merge-base <default-branch> HEAD, or the diff range the review pass reviewed). Only lines or regions the branch introduced are in scope. - Findings (optional): deslop-class review findings (redundant comments, over-defensive handling, unnecessary casts) to apply, when a review pass already produced them.
Process
- Resolve the diff:
git diff <base>...HEAD. Read each changed file's surrounding code so the strip matches local style, not your instinct. - Scan the diff for the strip classes:
- Redundant comments: comments that restate the code, are inconsistent with the file's style, or are commented-out code. Keep comments that carry a decision, a tradeoff, or a security gotcha (the kit's comment rule: explain WHY, not WHAT). When a name needs a comment to explain itself, prefer renaming over commenting (coding-hygiene).
- Over-defensive handling: defensive checks or try/catch blocks that are abnormal for the file's trusted code paths. A documented repo standard overrides this (for example
rules/frontend-ts.mdmandates try/catch around API calls); when the file's own pattern keeps the guard, keep it and flag it as kept. - Unnecessary casts: casts (
as anyand friends) used only to bypass a type error, where a real fix exists (narrow the type, use a proper type guard). A cast with a stated reason is not slop. - Flattenable nesting: deeply nested code in the changed lines that simplifies to early returns without changing behavior.
- Inconsistent patterns: code that contradicts the file and surrounding codebase (a second convention beside an existing one).
- Apply the strip with surgical edits. The minimum diff that removes the smell; never rewrite a function to fix one flagged line.
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.
- 4d ago First seen · 87 lines · 68 tokens per session scan A e5d36119de35
slop-stripper is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 1,210 once invoked, about $0.0003 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
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.