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 wrannaman/agentic-engineering --skill deslopgit clone --depth 1 https://github.com/wrannaman/agentic-engineeringWrote 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/wrannaman/agentic-engineering/deslop)<a href="https://agentmods.dev/skills/wrannaman/agentic-engineering/deslop"><img src="https://agentmods.dev/badge/skills/wrannaman/agentic-engineering/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/wrannaman/agentic-engineering/deslop"><img src="https://agentmods.dev/badge/skills/wrannaman/agentic-engineering/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 | $0.00143 | $0.01157 |
| Opus 5.5 | $0.00057 | $0.00463 |
| Sonnet 5.5 | $0.00029 | $0.00231 |
| Haiku 4.5 | $0.00014 | $0.00116 |
Grade A, and why
deslop-code 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 2mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aggressively reduce code. Every line must earn its place — strip AI artifacts, remove bloat, and shrink files to their essence while preserving clarity and correctness.
Scope
Default: files changed on the current branch vs main (git diff --name-only main...HEAD).
If the user specifies files, directories, or patterns, use those instead.
Process
- Get the file list for the scope above
- Read each file completely — understand what it does before touching it
- Apply reductions file by file, using all applicable techniques below
- After all edits, run any available tests/typecheck to confirm nothing broke
- Report: files modified, approximate lines removed, notable structural changes
Reduction Techniques
Apply in rough priority order. Each change should pass a simple test: "does the code still read clearly to someone seeing it for the first time?"
Delete dead code
- Unreachable branches, unused imports, unused variables, unused functions, unused types
- Feature flags that are always on/off
- Commented-out code — it's in git history if anyone needs it
Strip AI-generated noise
- Comments explaining obvious code (
// increment counterabovecount++) - Comments more detailed than surrounding file style
- Section headers/banners (
// TYPES ---,// CONSTANTS,// PUBLIC API) - Keep only comments explaining WHY, not WHAT
- Noisy logs:
console.log/loggercalls with no actionable information (keep errors, warnings, state transitions, external API calls)
Remove defensive bloat
try/catcharound code that cannot throw- Null checks on values already guaranteed non-null by the type system or prior logic
- Redundant parameter validation inside internal (non-boundary) functions
- Assertions that duplicate what the type system already enforces
- Exception: keep defensive code at system boundaries (network calls, file I/O, user input, external APIs)
Collapse indirection
- Inline functions/methods called exactly once (unless the name provides significant documentation value)
- Inline single-use variables:
const x = foo(); return x;→return foo(); - Flatten unnecessary wrappers:
const handleClick = () => doThing()→ passdoThingdirectly - Collapse single-implementation interfaces/abstractions — if there's only one implementation and no test mock, the abstraction isn't paying for itself yet
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.
- 2mo ago First seen · 91 lines · 143 tokens per session scan A 5618c87f7dd1
deslop-code is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 6mo ago), licensed MIT. It adds 143 tokens to every session and 1,157 once invoked, about $0.0006 per session on Opus 5.5. 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.
deslop-code compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deslop-codewrannaman/agentic-engineering | Skill | 2 | 6mo ago | MIT | A | 143 | Claude Code, Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 48 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 947 | 2d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | today | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |