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 BanibrataChatterjee/AwesomeSalesforceSkills --skill in-app-guidance-and-walkthroughsgit clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsWrote 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/banibratachatterjee/awesomesalesforceskills/in-app-guidance-and-walkthroughs)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/in-app-guidance-and-walkthroughs"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/in-app-guidance-and-walkthroughs/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/banibratachatterjee/awesomesalesforceskills/in-app-guidance-and-walkthroughs"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/in-app-guidance-and-walkthroughs.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 | $0.00085 | $0.02685 |
| Opus 5 | $0.00043 | $0.01342 |
| Sonnet 5 | $0.00017 | $0.00537 |
| Haiku 4.5 | $0.00009 | $0.00268 |
Grade A, and why
in-app-guidance-and-walkthroughs 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
In-App Guidance and Walkthroughs
This skill activates when a practitioner needs to design, configure, or troubleshoot Salesforce In-App Guidance — the platform's native mechanism for delivering contextual prompts and multi-step walkthroughs to users directly inside Lightning Experience. It covers prompt type selection, walkthrough authoring, audience filtering, scheduling, limit management, and adoption analytics.
Before Starting
Gather this context before working on anything in this domain:
- Confirm the org is on Lightning Experience. In-App Guidance does not function in Salesforce Classic or Experience Cloud (Guest/Partner portals require PRM licenses and use a different engine).
- Identify how many active custom walkthroughs the org already has. The free tier allows exactly 3 active walkthroughs. Exceeding that limit requires a Sales Enablement license (~$25/user/month as of Spring '25). Prompts created by AppExchange managed packages do not count against this cap.
- Determine which user profiles should see each prompt. Audience targeting is profile-based only as of Spring '25 — permission sets, roles, territories, and behavioral signals are not supported natively.
- Identify the anchor element for any targeted prompt. If the anchor UI element is removed or renamed in a future release or layout change, the targeted prompt will silently stop appearing with no error surfaced to admins.
Core Concepts
Prompt Types
Salesforce provides three prompt types, each with distinct behaviors and trade-offs:
Floating prompts are repositionable modal-style cards. The user can drag them to a different position on the page. They are the most flexible prompt type and work anywhere in Lightning Experience. Use them for org-wide announcements or general onboarding messages that do not need to point at a specific UI element.
Docked prompts appear anchored to the bottom corner of the screen. They support embedded video (YouTube or a direct video URL) and are designed for richer content such as feature overview clips. Because they stay docked rather than overlaying content, they have lower intrusion on user workflow. Use them when video is the primary communication medium.
What ships with it
6 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.
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 · 189 lines · 85 tokens per session scan A c13431b11fac
in-app-guidance-and-walkthroughs is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,685 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 2026-09-03.
Other skills, from other repositories
change-management-and-training
Use this skill when planning user adoption, structuring Salesforce training materials, drafting release communications, or running a change impact assessment for a Salesforce rollout or update. Triggers: user adoption plan, training materials, release announcement, change impact, go-live communication. NOT for org…
praxis-onboarding
Use when a new user wants to get started with Facets or Praxis hands-on, has a brand-new or empty control plane, or asks to 'onboard me', 'get me started', 'set up my first deployment', or 'resume onboarding'. Runs a guided journey, not a topic lookup.
pm-teaching-mode
Comprehensive teaching templates and progressive disclosure patterns for PM teacher mode.
subsystem-walkthrough
Walk through how a subsystem works: architecture, runtime flow, ownership, layering. Apply when the user asks "how does X work", "where should this live", or wants an onboarding mental model before changing code. Use design-rationale for motivation. Use dissect to audit entities. Use proving-change-safety before…
platform-management
Workspace OS charter for Auto — runtime governor of the agent organisation, routing, cadence, authority, governance, and full platform operations reference.
onboarding-culture-immersion
A new-hire onboarding approach that teaches company values and purpose through the employee’s first experiences. Onboarding is the process of helping someone start and become effective in a new job.