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 skills/speedpy/speedpy/strip-demonpx skills add speedpy/speedpy --skill strip-demogit clone --depth 1 https://github.com/speedpy/speedpyWrote 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/speedpy/speedpy/strip-demo)<a href="https://agentmods.dev/skills/speedpy/speedpy/strip-demo"><img src="https://agentmods.dev/badge/skills/speedpy/speedpy/strip-demo.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 | $0.00049 | $0.01146 |
| Opus 5 | $0.00024 | $0.00573 |
| Sonnet 5 | $0.00010 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
strip-demo 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/strip-demo — Strip demo content for production
Audit-first workflow for turning a SpeedPy fork into a clean production app skeleton. This skill reads the manifest and markers, produces a plan, and requires explicit confirmation before editing or deleting anything.
Prerequisites
Read these files before starting:
AGENTS.md/AGENTS-local.md— project conventions and mode-specific commandsPRODUCTION_READY.md— human checklist (the source of truth for removal steps)demo-content.json— machine-readable manifest of all demo artifacts
Workflow
Phase 1 — Audit (read-only, always safe)
-
Parse the manifest. Read
demo-content.jsonand list every artifact by category. -
Scan for markers. Run
rg SPEEDPY_DEMOacross the project. Cross-reference with the manifest to confirm every marker is accounted for. -
Check path existence. For each artifact in the manifest, verify whether its paths exist in the current working tree. Note any already-removed items.
-
Detect database state. Determine if this is a fresh clone (no production data) or an existing database:
- If
demoapp/migrations/exists and migrations have been applied, warn about data migration needs. - Ask the user to confirm their scenario.
- If
-
Identify test dependencies. Check which test files import from
demoappor reference demo API endpoints. List these as items that need migration to non-demo endpoints. -
Present the removal plan. Organize findings into sections matching
PRODUCTION_READY.md:- Items to delete (
safe_remove) - Items to review before deciding (
review) - Items to replace with fork-owner content (
replace) - Test files that need endpoint migration
- Database actions needed (if existing DB)
- Items to delete (
Stop here and ask for confirmation. Do not proceed to Phase 2 without explicit user approval.
Phase 2 — Execute (destructive, only after confirmation)
Only perform removals that the user explicitly approved. For each approved section:
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.
- 5d ago First seen · 105 lines · 49 tokens per session scan A d9bfe75a0ba9
strip-demo is a skill published in the GitHub repository speedpy/speedpy (79 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,146 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 2026-08-30.
Other skills, from other repositories
django-celery-expert
Expert Django Celery guidance for asynchronous task processing. Use when designing background tasks, configuring Celery workers, handling task retries and errors, optimizing Celery performance, implementing periodic tasks with Celery Beat, or setting up production monitoring for Celery. Do not use for general Django…
django-expert
Expert Django backend development guidance. Use when creating Django models, views, serializers, or APIs; debugging ORM queries or migrations; optimizing database performance; implementing authentication; writing tests; or working with Django REST Framework. Follows Django best practices and modern patterns.
run-backend
Start the DARE backend locally — Django ASGI on port 8000, plus the Redis and .env prerequisites it needs. Use when the user wants to run, start, boot, or serve the DARE backend, or asks why the API on :8000 is not responding.
run-workers
Start and check the DARE RQ background workers that process file uploads (parse, chunk, embed, upsert to the vector store). Use when the user uploads or vectorizes files, works on RAG ingestion, or asks why an uploaded file is stuck and never reaches "completed".
check
Run the DARE backend's local check suite — Black, isort, and the Django test suite — before opening a pull request. Use when the user is about to commit, push, or open a PR, or asks whether their change passes CI.
prettify
Iteratively improves the visual design of an existing page — making it more sophisticated, richer, and prettier — without redesigning from scratch. Works on any page or UI surface: landing pages, marketing pages, pricing, docs, dashboards, admin views, settings, modals, empty states, etc. Use when the user says…