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/setupgit 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/setup)<a href="https://agentmods.dev/commands/forcedotcom/sf-skills/setup"><img src="https://agentmods.dev/badge/commands/forcedotcom/sf-skills/setup.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 | $0.00047 | $0.00813 |
| Opus 5 | $0.00023 | $0.00407 |
| Sonnet 5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
setup 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the tool prerequisite scan and render an actionable status report.
Phase 1: Scan
${CLAUDE_PLUGIN_ROOT}/scripts/sf-context check-tools
The output is a JSON object with a tools array (plus a diagnostic block on any critical failure).
The banner is painted for you — do not reproduce it. When check-tools runs, the plugin paints the framed "Ready to build on Salesforce?" banner deterministically on the visible channel (one status row per tool, the footer verdict, and the wayfinding footer), exactly like the SessionStart banner. Read the JSON for your own understanding, but do NOT reproduce, redraw, or re-render the banner — add only a short read of what it means for the user, then go to Phase 2.
Only if you do not see the banner painted (an older Claude Code build, or a paint fallback) render it yourself from the JSON, using the layout defined in the platform-environment-validate skill as the single source of truth. Read ${CLAUDE_PLUGIN_ROOT}/skills/platform-environment-validate/SKILL.md (Phase 1) for the canonical frame, status-dot definitions, fixed row order, footer verdict, and wayfinding footer. In brief: one framed block, one row per tool with a 🔴/🟡/🟢/ℹ️ status dot in a fixed order, and a footer verdict — ✓ toolchain ready when there are no 🔴/🟡 rows, or ⚠ <N> need attention · <M> ready otherwise — then the "You don't memorize commands here." wayfinding block ending in a context-aware Next: <action> → "<phrase>" line. A setup is "all green" when there are no 🔴 or 🟡 rows; ℹ️ rows never count against it.
Deterministic results — do NOT override a failure. The JSON report is the authoritative result. If a tool reports 🔴/🟡, render it as-is; never re-run the check a different way and present the result as 🟢. When the report includes a diagnostic block (attached on any critical failure), surface it — it carries platform, active shell, working directory, plugin root, and the resolved executable paths, and is secret-free by design.
Note: the Code Analyzer plugin is a JIT ("just-in-time") plugin — if it is registered but not yet physically installed, check-tools reports it 🟢 with a note that it auto-installs on first sf code-analyzer run. That is expected and not a problem.
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 · 39 lines · 47 tokens per session scan A cfb3c7c93ce4
setup is a command published in the GitHub repository forcedotcom/sf-skills (961 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 813 once invoked, about $0.0002 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.