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 agentmods add commands/forcedotcom/sf-skills/logingit 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/commands/forcedotcom/sf-skills/login)<a href="https://agentmods.dev/commands/forcedotcom/sf-skills/login"><img src="https://agentmods.dev/badge/commands/forcedotcom/sf-skills/login.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00511 |
| Opus 5 | $0.00013 | $0.00255 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
login scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Authenticate to a Salesforce org. The user can pass:
--alias <name>to label the auth (e.g.,myDevHub,customerSandbox)--instance-url <url>for non-production endpoints (e.g.,https://test.salesforce.comfor sandboxes,https://login.salesforce.comfor production — production is the default if omitted)--set-defaultto set this org as the project'starget-orgafter auth
Workflow:
-
Parse the arguments ($ARGUMENTS) the user provided. Extract alias, instance-url, and set-default flag.
-
Run the login command:
sf org login web {--alias $ALIAS} {--instance-url $URL}This opens a browser for OAuth. Tell the user clearly: "A browser window will open. Complete the login flow and return here."
-
Handle browser-isn't-available case: If the user is on a remote shell or the browser won't open, fall back to:
sf org login device-code {--alias $ALIAS} {--instance-url $URL}which prints a code the user enters at salesforce.com/setup/connect.
-
After successful auth: if the user passed
--set-default, run:sf config set target-org $ALIASOtherwise, suggest they run
/salesforce-development:set-default <alias>if they want to use this org for the current project. -
Verify: print a one-liner with the new org's alias, edition, and instance URL:
sf org display --target-org $ALIAS --jsonso the user sees the connected state.
Rules:
- Always use
--jsononsfcommands so you can parse outcomes - Do NOT log access tokens or any auth secrets
- If the user doesn't supply an alias, the auth saves under their username — recommend they pass
--aliasfor easier reference later - For sandbox auth,
--instance-url https://test.salesforce.comis required
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.
- today First seen · 46 lines · 26 tokens per session scan A 7e5b223eb552
login is a command published in the GitHub repository forcedotcom/sf-skills (961 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 511 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.