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 dashaworks/share-as-link-skill --skill share-as-linkgit clone --depth 1 https://github.com/dashaworks/share-as-link-skillWrote 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/dashaworks/share-as-link-skill/share-as-link)<a href="https://agentmods.dev/skills/dashaworks/share-as-link-skill/share-as-link"><img src="https://agentmods.dev/badge/skills/dashaworks/share-as-link-skill/share-as-link/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/dashaworks/share-as-link-skill/share-as-link"><img src="https://agentmods.dev/badge/skills/dashaworks/share-as-link-skill/share-as-link.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00104 | $0.00865 |
| Opus 5.5 | $0.00042 | $0.00346 |
| Sonnet 5.5 | $0.00021 | $0.00173 |
| Haiku 4.5 | $0.00010 | $0.00086 |
Grade A, and why
share-as-link 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Share as Link
The zero-friction "get me a link" skill. Something worth keeping was just produced — publish it as-is to a live URL and hand the link back. No restructuring, no redesign, no "let me turn this into a report first." That restraint is the whole point: it keeps this a ten-second operation.
When to use
- "Share this / give me a link / put this online / make it a page"
- The user wants the content out of the chat now, not improved
- The output is already in a shape the user is happy with — they just need a URL
When not to use — hand off instead:
- The content should be reshaped into a real document with sections, hierarchy, and charts → report-publisher
- It's going to a specific person and knowing "did they open it?" matters → proposal-tracker
- It's slides → deck-publisher
Offer the handoff when you see the need; don't silently upgrade a "just give me a link" request into a full report.
Steps
- Take the content as-is. Use what was just produced verbatim — the conversation excerpt, the analysis, the markdown, the artifact. Do not rewrite, reorder, or "improve" it. Light cleanup only: a title, and stripping obvious chat scaffolding ("sure, here's…").
- Author minimally. Call
get_design_systemand wrap the content in the design system's basic document shell so it reads well — themed type, spacing, dark mode — but add no structure the source didn't have. For plain markdown,publishMode B (content+type: "report") is the fastest path; for richer content author light HTML. - Lint. Call
lint_documentand fix what it flags. Even the fast path passes lint. - Publish. Call
publish. Return the live URL prominently and plainly — the link is the deliverable. - Then, and only then, offer the upgrades. One short line, not a pitch:
- "Want this designed properly as a report?" → report-publisher
- "Sending it to someone specific and want to know if they open it?" → proposal-tracker
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.
- 1mo ago First seen · 62 lines · 104 tokens per session scan A 80e08267aa2c
share-as-link is a skill published in the GitHub repository dashaworks/share-as-link-skill (220 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 865 once invoked, about $0.0004 per session on Opus 5.5. 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
rudder-data-graphs
Produces Data Graph YAML from RETL sources for Audiences. Use when designing Data Graphs, mapping RETL to entities/events, or assessing customer fit for Audiences.
rudder-typer-workflow
Generates type-safe SDKs (Swift/Kotlin) from tracking plans with compile-time validation. Use when generating type-safe event tracking code from tracking plans using RudderTyper.
rudder-instrumentation-planning
Designs event taxonomies and instrumentation strategies from business requirements. Use when designing event taxonomy from scratch or restructuring existing instrumentation strategy.
rudder-instrumentation-debugging
Diagnoses and fixes validation errors, schema issues, and instrumentation problems. Use when debugging validation errors, schema issues, or instrumentation problems.
rudder-ai-events-verify
Verifies RudderStack AI events locally and checks a move from existing RudderStack events: validates captures against the v0.3 schema, joins, switches and legacy events. Use when testing AI events, comparing old and new tracking, or when AI or MCP events look wrong or missing.