Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add j-256/agent-skills/plugin install dscWrote 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/j-256/agent-skills/dsc-scrape)<a href="https://agentmods.dev/skills/j-256/agent-skills/dsc-scrape"><img src="https://agentmods.dev/badge/skills/j-256/agent-skills/dsc-scrape/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/j-256/agent-skills/dsc-scrape"><img src="https://agentmods.dev/badge/skills/j-256/agent-skills/dsc-scrape.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 | $0.00083 | $0.03854 |
| Opus 5 | $0.00042 | $0.01927 |
| Sonnet 5 | $0.00017 | $0.00771 |
| Haiku 4.5 | $0.00008 | $0.00385 |
Grade A, and why
dsc-scrape 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 9d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DSC Doc Scraping
Inputs
url(required) -- a DSC URL: either the top-level/docs/apiscatalog, a product-area landing/docs/<product>/<area>/references, a specific reference root/docs/<product>/<area>/references/<name>, or a single slug.../references/<name>?meta=<slug>.out(required) -- an absolute path to the output root directory.
If the user's request is vague ("pick one from Commerce Cloud", "scrape any endpoint from Data Cloud"), bootstrap from the top-level catalog: scrape https://developer.salesforce.com/docs/apis first, read the resulting <out>/_catalog.json, pick the product whose title matches the user's request, and follow its referenceUrl into the area-landing scrape. Each product in the catalog has title, body (short description), referenceUrl, referenceShape, and searchKeys (an array of acronyms and synonyms drawn from the product's landing page plus a hand-curated map for community jargon like "SCAPI"). Match the user's hint case-insensitive substring against title, body, and searchKeys together – the third surface is what makes acronyms like "OCI" or "FSC" resolve without depending on the model's training data. The referenceShape tells you whether the reference target is scrapeable (area-landing, reference-root) or out-of-scope (atlas, static-html).
Catalog product names drift from what a user might say. Salesforce has rebranded "Data Cloud" to Data 360, for example, so matching the literal string "Data Cloud" against catalog titles finds nothing; match on topic keywords. A handful of products (notably Marketing Cloud Growth / Marketing Cloud Next, and Agentforce) don't surface in /docs/apis at all but do have /references/ pages reachable by direct URL. After a catalog miss, lowercase the user's hint and substring-match it against the keys in shared/scrape/aliases.js (the CATALOG_MISSING_ALIASES map) before asking the user for a URL. Don't substitute a related-looking product when the catalog and alias map both miss – e.g. for "Agentforce" the catalog returns no match and the alias map is the canonical next step, not Einstein Gen AI or any other product whose name overlaps semantically. If both miss, ask the user for a URL.
What ships with it
60 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.
- examples/scrape-agentforce-references.md 1.6 KB
- README.md 16 KB
- scripts/scrape.js 191 B runs code
- shared/common/body-values.js 3.6 KB runs code
- shared/common/cite.js 677 B runs code
- shared/common/live-test.js 4.3 KB runs code
- shared/common/parse-request.js 6.7 KB runs code
- shared/common/pkce.js 679 B runs code
- shared/common/resolve-slug.js 6.9 KB runs code
- shared/common/scrape-refresh.js 2.4 KB runs code
- shared/common/shell-vars.js 1.3 KB runs code
- shared/common/spec-traversal.js 2.8 KB runs code
- shared/engine/auth-providers.js 3.8 KB runs code
- shared/engine/curated-facts.js 9.7 KB runs code
- shared/package-lock.json 183 B
- shared/package.json 245 B
- shared/products/commerce-b2c/auth-providers.js 7.5 KB runs code
- shared/products/commerce-b2c/auth-render.js 15 KB runs code
- shared/products/commerce-b2c/curated-facts.js 22 KB runs code
- shared/products/commerce-b2c/dedupe-scopes.js 2.7 KB runs code
- shared/products/commerce-b2c/live-baskets.js 2.0 KB runs code
- shared/products/commerce-b2c/persona.js 1013 B runs code
- shared/products/commerce-b2c/slas-flows.js 4.1 KB runs code
- shared/scrape/aliases.js 2.3 KB runs code
- shared/scrape/cache-access.js 5.2 KB runs code
- shared/scrape/cache-path.js 804 B runs code
- shared/scrape/catalog-keys.js 1.4 KB runs code
- shared/scrape/classify.js 2.2 KB runs code
- shared/scrape/extract-keys.js 2.6 KB runs code
- shared/scrape/fetch-url.js 5.4 KB runs code
- shared/scrape/load-yaml.js 311 B runs code
- shared/scrape/parse-amf.js 11 KB runs code
- shared/scrape/parse-api-catalog.js 1.5 KB runs code
- shared/scrape/parse-catalog.js 1.0 KB runs code
- shared/scrape/parse-oas.js 6.6 KB runs code
- shared/scrape/parse-swagger2.js 5.3 KB runs code
- shared/scrape/reference-versions.js 4.5 KB runs code
- shared/scrape/resolve-cache.js 4.4 KB runs code
- shared/scrape/scrape.js 19 KB runs code
- shared/scrape/write-slugs.js 1.5 KB runs code
- shared/test/fixtures/fake-scrape.js 4.0 KB runs code
- shared/test/fixtures/no-basepath-index.json 580 B
- shared/test/fixtures/ocapi-shop-customers-index.json 521 B
- shared/test/fixtures/shopper-orders-index.json 2.0 KB
- shared/test/run.sh 568 B runs code
- shared/test/test-aliases-live.js 1.5 KB runs code
- shared/test/test-aliases.js 1.4 KB runs code
- shared/test/test-body-values.js 1.8 KB runs code
- shared/test/test-cache-access.js 6.7 KB runs code
- shared/test/test-cache-path.js 1.5 KB runs code
- shared/test/test-catalog-keys-live.js 1.7 KB runs code
- shared/test/test-catalog-keys.js 2.0 KB runs code
- shared/test/test-cite.js 1.5 KB runs code
- shared/test/test-dependency-direction.js 1.2 KB runs code
- shared/test/test-extract-keys.js 3.2 KB runs code
- shared/test/test-fetch-url.js 1.7 KB runs code
- shared/test/test-live-test.js 2.4 KB runs code
- shared/test/test-load-yaml.js 1.8 KB runs code
- shared/test/test-parse-oas.js 6.6 KB runs code
- shared/test/test-parse-request.js 5.0 KB runs code
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.
- 9d ago First seen · 146 lines · 83 tokens per session scan A dc14d4487135
dsc-scrape is a skill published in the GitHub repository j-256/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 83 tokens to every session and 3,854 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 2026-08-31.
Other skills, from other repositories
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
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.
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.
liveview-patterns
Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.