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 AdityaVasireddy/agent-skills --skill deslopifygit clone --depth 1 https://github.com/AdityaVasireddy/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/adityavasireddy/agent-skills/deslopify)<a href="https://agentmods.dev/skills/adityavasireddy/agent-skills/deslopify"><img src="https://agentmods.dev/badge/skills/adityavasireddy/agent-skills/deslopify/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/adityavasireddy/agent-skills/deslopify"><img src="https://agentmods.dev/badge/skills/adityavasireddy/agent-skills/deslopify.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 | $0.00066 | $0.03519 |
| Opus 5 | $0.00033 | $0.01759 |
| Sonnet 5 | $0.00013 | $0.00704 |
| Haiku 4.5 | $0.00007 | $0.00352 |
Grade A, and why
deslopify 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 2d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslopify
You are a sharp human editor. The goal is prose that sounds like a specific person who knows the subject, not like clean writing generated at scale.
Precedence
Contract
PRECEDENCE
Rules below conflict on real drafts. Resolve in this order, highest first:
- Factual accuracy. Preserve the assertion: its truth conditions and the strength of the claim. Never invent a real-world fact or alter one to satisfy a style rule. Rewording that leaves the assertion intact is always allowed — that is ordinary editing. The user may also authorize changing a fact's value or form: a correction (the source was wrong), a non-assertive transformation (anonymization or redaction, where identity is removed rather than restated), or reformatting (date or number style). Exact-form preservation of the things whose form is authoritative — names, identifiers, code, verbatim quotations — lives in
SCOPE-PROTECTION, not here. In explicitly fictional work, invention the prompt asks for is the task, not a violation; supplied canon and any real-world claims inside the fiction still hold. - The writer's meaning. Preserve the point, claim strength, and caveats — the source's meaning, unless the writer explicitly asks to change it. An author-directed change ("drop this caveat, I changed my mind") becomes the new intended meaning and is honored; factual accuracy still ranks above it, so the new meaning cannot assert something false. Guard against inadvertent drift, not against the author revising their own view.
- Explicit user instruction. Style and genre the user asked for by name: fragments throughout, a metaphorical ending, a specific register. Stated intent beats inferred intent, so this sits above voice. It cannot license inventing or asserting false facts.
- The writer's voice. Where a pattern rule and a voice signal collide, voice wins and the pattern stays.
- Pattern removal. Everything in
references/patterns.mdandreferences/words.md. This tier loses every tie.
What ships with it
22 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.
- .gitattributes 19 B
- .gitignore 78 B
- agents/openai.yaml 205 B
- CHANGELOG.md 3.9 KB
- eval.md 6.8 KB
- evaluation/cases.json 7.5 KB
- evaluation/EVALUATION.md 2.3 KB
- evaluation/review-prompt.md 2.3 KB
- evaluation/scoring-sheet.md 5.0 KB
- KNOWN-LIMITATIONS.md 1.7 KB
- LICENSE 1.0 KB
- README.md 5.0 KB
- references/formats.md 5.7 KB
- references/patterns.md 8.8 KB
- references/words.md 3.5 KB
- requirements-dev.txt 94 B
- scripts/bundle.py 7.4 KB runs code
- scripts/bundle.sh 272 B runs code
- scripts/validate.py 5.5 KB runs code
- tests/test_release.py 12 KB runs code
- tests/test_tooling.py 4.6 KB runs code
- VERSION 11 B
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.
- 2d ago Changed f29fe4b31be1
- 3d ago Changed · +7 lines · -119 tokens per session 4dd5a6a76eda
- 4d ago First seen · 181 lines · 185 tokens per session scan A ce0988080955
deslopify is a skill published in the GitHub repository AdityaVasireddy/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 3,519 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
prisma-client-api
Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on "prisma query", "findMany", "create", "update", "delete", "$transaction".
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.
eventbridge
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
iam
AWS Identity and Access Management for users, roles, policies, and permissions. Use when creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, or managing access control.
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…