Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsnpx agentmods add commands/banibratachatterjee/awesomesalesforceskills/request-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/commands/banibratachatterjee/awesomesalesforceskills/request-skill)<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/request-skill"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/request-skill/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/commands/banibratachatterjee/awesomesalesforceskills/request-skill"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/request-skill.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 | $0.00000 | $0.00963 |
| Opus 5 | $0.00000 | $0.00481 |
| Sonnet 5 | $0.00000 | $0.00193 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
request-skill 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/request-skill — Report a Missing Skill
Use this when you know a skill is missing but don't want to build it yourself.
Takes 4 questions, checks existing coverage, and adds a TODO row to MASTER_QUEUE.md.
Step 1 — Ask the 4 questions
Ask the user exactly these questions. Ask all 4 upfront, not one at a time:
1. What Salesforce task does this skill cover?
(Describe it as a task someone performs, not a feature name)
Example: "Configure case assignment rules in Service Cloud"
Not: "Case assignment rules"
2. Who is this skill for?
Admin / BA / Developer / Data / Architect
3. Which Salesforce cloud does this apply to?
Core Platform / Sales Cloud / Service Cloud / Experience Cloud /
Marketing Cloud / Revenue Cloud / Field Service / Health Cloud /
Financial Services Cloud / Nonprofit Cloud / Commerce Cloud /
Agentforce / OmniStudio / CRM Analytics / Integration / DevOps
4. What's the main problem it solves or mistake it prevents?
(One sentence)
Step 2 — Check for existing coverage
cd /path/to/SfSkills
python3 scripts/search_knowledge.py "<task from question 1>"
python3 scripts/search_knowledge.py "<task from question 1>" --domain <domain>
If has_coverage: true:
Show the user the existing skill. Ask: "Does this cover what you need, or is your use case different enough to warrant a new skill?"
- If covered → stop. Point them to the existing skill.
- If different → continue with a clear disambiguation note.
If has_coverage: false:
Continue.
Step 3 — Determine domain and skill name
Map role → domain:
Admin / BA / Architect role → admin
Developer role → most specific: apex / lwc / flow / integration / devops
Data role → data
OmniStudio topics → omnistudio
Agentforce topics → agentforce
Security topics → security
Generate a kebab-case skill name from the task:
- "Configure case assignment rules" →
case-assignment-rules - "Set up territory management for Sales Cloud" →
sales-cloud-territory-management - "Apex callout error handling patterns" →
callout-error-handling
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 · 138 lines · 0 tokens per session scan A 9be69fe30d34
request-skill is a command published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 963 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.