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 forcedotcom/sf-skills --skill experience-content-media-searchgit clone --depth 1 https://github.com/forcedotcom/sf-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/forcedotcom/sf-skills/experience-content-media-search)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-content-media-search"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-content-media-search/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/forcedotcom/sf-skills/experience-content-media-search"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-content-media-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 85 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 89 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 116 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00210 | $0.03082 |
| Opus 5 | $0.00105 | $0.01541 |
| Sonnet 5 | $0.00042 | $0.00616 |
| Haiku 4.5 | $0.00021 | $0.00308 |
Grade A, and why
experience-content-media-search 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 11d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Search
Universal routing skill for searching and retrieving existing images and media.
Scope
This skill is for SEARCHING FOR existing media, not CREATING new media.
Use this skill when the user wants to:
- Search for images in Salesforce CMS, Data Cloud
- Find existing visual assets to use in their app
- Retrieve media from connected sources
- Browse available images for their project
- Locate specific photos or graphics
DO NOT use this skill when the user wants to:
- Generate new images with AI (use image generation tools)
- Create graphics or designs from scratch
- Edit or modify existing images
- Build custom visuals or diagrams
- Search for stock photography or royalty-free images (use
experience-content-media-stock-image-search)
Before You Search
CRITICAL: This is a routing skill, not a direct search skill.
When a user requests to find an image:
Your first action MUST use the ask_followup_question tool to present search sources.
- Use ask_followup_question to present available search sources as options
- Receive the user's selection from the tool response
- Then call the appropriate search tool based on their choice
Example of what NOT to do:
- Calling ANY tool before the user picks a source (MCP tools, file reads, descriptor checks, etc.)
- "Checking which MCP tools are available" — do not probe or discover tools via tool calls
- Immediately calling
search_electronic_mediaorsearch_media_cms_channels - Reading MCP tool descriptors or schemas to see what's available
- Deciding which search source to use without asking
Example of what TO do:
- Respond with ONLY text — a numbered list of search sources
- Ask: "Which option would you like to use?"
- Wait for user to reply with their choice
- Then (and only then) call the tool they selected
Your first response when this skill triggers MUST be a text-only message presenting search sources. No tool calls. No exceptions.
Workflow Overview
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.
- 11d ago First seen · 354 lines · 210 tokens per session scan A 1fcf29ac4bfa
experience-content-media-search is a skill published in the GitHub repository forcedotcom/sf-skills (981 stars, last pushed 2d ago), licensed Apache-2.0. It adds 210 tokens to every session and 3,082 once invoked, about $0.0011 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.