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 mikecann/agent-skills --skill deslopgit clone --depth 1 https://github.com/mikecann/agent-skillsWrote 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/mikecann/agent-skills/deslop)<a href="https://agentmods.dev/skills/mikecann/agent-skills/deslop"><img src="https://agentmods.dev/badge/skills/mikecann/agent-skills/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/mikecann/agent-skills/deslop"><img src="https://agentmods.dev/badge/skills/mikecann/agent-skills/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 | $0.00075 | $0.00976 |
| Opus 5 | $0.00037 | $0.00488 |
| Sonnet 5 | $0.00015 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00098 |
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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslop
Take code that was just written and make it feel tighter, simpler, and more deliberate.
Read style.md first. That file is the source of truth for the style rules.
Process
- Identify the target files.
- Start with files modified in this session.
- Use
git diffif available, otherwise use recent edits or the user's explicit file list. - Do not touch unrelated files.
- Read each target file before editing it.
- Use parallel subagents for the cleanup pass.
- If there are multiple files, split them across subagents.
- If there is one large file, it is still fine to use one subagent for an isolated second pass.
- Give each subagent the exact file list it owns.
- If the scope is only one to three small files, a single pass is fine. Do not add subagent overhead just to satisfy the rule mechanically.
- Tell each subagent to:
- read
skills/deslop/style.md - simplify only its assigned files
- preserve behavior exactly
- skip any change that adds churn without making the code clearer
- report a short summary of what changed and what was intentionally skipped
- read
- Review the subagent output, apply the changes, then do a final sanity pass yourself.
- Summarise the cleanup in concrete terms.
- Example: "flattened 3 nested conditionals, renamed 2 booleans, replaced 1 non-null assertion"
Constraints
- Never change behavior. This is a style pass, not a refactor.
- If a style rule conflicts with preserving behavior, preserving behavior wins.
- Prefer small, local edits over wide rewrites.
- If the code only becomes meaningfully cleaner after a deeper architectural refactor, stop and say so instead of forcing deslop beyond its scope.
- Skip generated files, vendor code, build output, and lockfiles.
- Skip tests unless the user asked to include them.
- Skip any rule when applying it would make the code harder to read.
- Preserve exported and public APIs unless the user explicitly asked for API changes.
- Preserve exported TypeScript signatures unless the user explicitly asked for typing or API changes.
- If the code is already clean, say that instead of forcing changes.
What ships with it
1 file 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 · 106 lines · 75 tokens per session scan A de57e5a12338
deslop is a skill published in the GitHub repository mikecann/agent-skills (21 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 976 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.