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 jscraik/Agent-Skills --skill agent-ops-unslopifygit clone --depth 1 https://github.com/jscraik/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/jscraik/agent-skills/agent-ops-unslopify)<a href="https://agentmods.dev/skills/jscraik/agent-skills/agent-ops-unslopify"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/agent-ops-unslopify/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/jscraik/agent-skills/agent-ops-unslopify"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/agent-ops-unslopify.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 | $0.00030 | $0.01676 |
| Opus 5 | $0.00015 | $0.00838 |
| Sonnet 5 | $0.00006 | $0.00335 |
| Haiku 4.5 | $0.00003 | $0.00168 |
Grade A, and why
unslopify 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 12d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unslopify Mode
Task: $ARGUMENTS
Philosophy
Make cleanup boring, scoped, and reversible. Unslopify should turn vague code-quality discomfort into evidence, a small cleanup ledger, and validation proof before edits happen.
Unslopify is a cleanup-only maintenance workflow. It is not for broad architecture redesign.
Canonical workflow is this file; $unslopify is the handle that routes to it.
When to use
Use Unslopify when the user asks for focused cleanup in an owned code scope with low architectural blast radius:
- unused/dead code
- stale exports, dependencies, or duplicate artifacts
- minor type hygiene risks with direct local evidence
- small circular dependency simplification
- brittle error handling patterns that hide real failures
Required inputs
- A target scope (file/folder/package/feature/route).
- A success condition for cleanup quality.
- Any constraints (risk tolerance, speed, scope lock).
- Optional baseline outputs (tests/lint/typecheck).
Mark these as out-of-scope and escalate:
- architectural redesigns
- package or API boundary changes
- cross-surface redesigns
- migration or contract changes
Deliverables
- Scoped cleanup ledger: finding, classification, rationale.
- Risk register for risky edits with rollback notes.
- Validation report with exact command + pass/fail + blocker evidence.
- Short handoff note for remaining work.
- Schema-bound outputs include
schema_version.
Failure mode
- If discovery is thin, baseline validation is missing, or any visibility gate fails, stop and report blocker-first.
- Fail fast: stop at the first failed gate, do not continue implementation, and rerun the failed gate only after the blocker is fixed.
Gotchas
- Resolver output is not enough by itself.
blocked_catalog_paritycan hide runtime mentionability even when handles exist.- Avoid claiming safe deletion when imports/references were not validated first.
The Workflow
Phase 1: Quick scan (limited, read-only)
- Run a short orientation pass for language/tooling and validation commands.
- Confirm generated/vendor/public API boundaries.
- Do not edit yet.
What ships with it
3 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.
- 12d ago First seen · 204 lines · 30 tokens per session scan A bcb292cfd59a
unslopify is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,676 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
prepare-pr
A pull-request preparation workflow for a software branch. A pull request is a request for teammates to review and merge a set of code changes.
refactoring
Safely refactor code while maintaining behavior. Use when improving code structure, reducing duplication, extracting functions, or modernizing legacy code.
code-review
Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.
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"…
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
pr-review-expert
Review GitHub PRs or GitLab MRs for correctness, security, compatibility, and affected test coverage, with actionable evidence tied to the diff.