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/divingsbysangam/salesforce-compound-engineering-pluginnpx agentmods add skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-compoundWrote 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/divingsbysangam/salesforce-compound-engineering-plugin/sf-compound)<a href="https://agentmods.dev/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-compound"><img src="https://agentmods.dev/badge/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-compound.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.01404 |
| Opus 5 | $0.00051 | $0.00702 |
| Sonnet 5 | $0.00020 | $0.00281 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
sf-compound 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 8d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sf-compound
Principles enforced: 5 (taste and oversight), 7 (institutional memory). See
PRINCIPLES.md.
Persona dispatch. This skill dispatches personas as isolated subagents — see the
dispatching-parallel-personasskill for the mechanics (isolated subagents, same-response parallelism, same-file-conflict check). Any reviewer/researcher it invokes (e.g.sf-learnings-researcher) is a research persona referenced from../sf-plan/references/personas/.
Copy-paste-to-agent
Capture learnings from completed Salesforce work into docs/solutions/ as YAML-frontmatter
solution documents validated against schema.yaml. Capture two kinds of learning explicitly:
(1) bug-fix learnings (symptom → root cause → resolution → prevention) and (2) aesthetic
or pattern learnings (the "works but gross" code we cleaned up, the abstraction we picked,
the convention we standardized on). Search existing solutions first — update existing
entries instead of duplicating. Update CLAUDE.md, agents, and skills only when the
learning generalizes beyond a single solution.
<feature_description> #$ARGUMENTS </feature_description>
Interaction Method
When asking the user a question, use the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex, ask_user in Gemini. Fall back to numbered options in chat only when no blocking tool exists in the harness or the call errors. Never silently skip the question.
Ask one question at a time. Prefer a concise single-select choice when natural options exist.
You are capturing learnings from completed work into the institutional knowledge system. Every solution documented makes the next iteration smarter.
Goal
Analyze recent work and capture learnings: $ARGUMENTS.scope
If no scope specified, analyze recent commits and changes.
The Compound Loop
Brainstorm (10%) → Plan (30%) → Work (20%) → Review (20%) → Compound (20%) → Repeat
│
└── YOU ARE HERE
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.
- 8d ago First seen · 182 lines · 101 tokens per session scan A f2e21c2b525b
sf-compound is a skill published in the GitHub repository divingsbysangam/salesforce-compound-engineering-plugin (10 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 1,404 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…