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 divingsbysangam/salesforce-compound-engineering-plugin --skill agentforce-observegit clone --depth 1 https://github.com/divingsbysangam/salesforce-compound-engineering-pluginWrote 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/agentforce-observe)<a href="https://agentmods.dev/skills/divingsbysangam/salesforce-compound-engineering-plugin/agentforce-observe"><img src="https://agentmods.dev/badge/skills/divingsbysangam/salesforce-compound-engineering-plugin/agentforce-observe.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 | $0.00160 | $0.00991 |
| Opus 5 | $0.00080 | $0.00495 |
| Sonnet 5 | $0.00032 | $0.00198 |
| Haiku 4.5 | $0.00016 | $0.00099 |
Grade A, and why
agentforce-observe 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agentforce-observe
Principles enforced: 7 (outsource thinking, not understanding), 3 (jagged intelligence in production), 5 (taste / drift detection), 1 (preserve the quality ceiling). See
PRINCIPLES.md.
Required reads
Procedure lives in sibling files, not only in this orchestrator:
-
When to use this skill — read
references/when-to-use-this-skill.mdbefore acting on this section. -
Inputs to gather before starting — read
references/inputs-to-gather-before-starting.mdbefore acting on this section. -
Phase 0: Discover the Data Space — read
references/phase-0-discover-the-data-space.mdbefore acting on this section. -
Phase 1: Observe — query STDM (preferred path) — read
references/phase-1-observe-query-stdm-preferred-path.mdbefore acting on this section. -
Phase 1-ALT: Fallback when STDM is unavailable — read
references/phase-1-alt-fallback-when-stdm-is-unavailable.mdbefore acting on this section. -
Phase 2: Reproduce — live preview, 3-run classification — read
references/phase-2-reproduce-live-preview-3-run-classification.mdbefore acting on this section. -
Phase 3: Improve — edit the
.agentfile directly — readreferences/phase-3-improve-edit-the-agent-file-directly.mdbefore acting on this section. -
Capture learnings — read
references/capture-learnings.mdbefore acting on this section. -
Inspiration — read
references/inspiration.mdbefore acting on this section.
Copy-paste-to-agent
Improve a deployed Agentforce agent using session-trace evidence. Three phases: (1) Observe
— query STDM session traces from Data Cloud (or fall back to sf agent test + sf agent preview
--authoring-bundle when STDM is unavailable); (2) Reproduce — re-run problematic conversations
in sf agent preview, classify CONFIRMED / INTERMITTENT / NOT REPRODUCED across 3 runs; (3)
Improve — edit the .agent file with targeted fixes, validate, publish, activate, then verify
in preview and post 24-48h re-run Phase 1 against baseline. Always pass --json on every sf
CLI command. Always re-run safety probes after any fix. Fail-closed: if STDM cannot run,
use Phase 1-ALT and record `stdm=unavailable: <reason>` — do not invent production
evidence. If preview also cannot run, stop; do not mark the issue reproduced.
What ships with it
9 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.
- references/capture-learnings.md 804 B
- references/inputs-to-gather-before-starting.md 4.9 KB
- references/inspiration.md 1.5 KB
- references/phase-0-discover-the-data-space.md 3.7 KB
- references/phase-1-alt-fallback-when-stdm-is-unavailable.md 8.0 KB
- references/phase-1-observe-query-stdm-preferred-path.md 6.5 KB
- references/phase-2-reproduce-live-preview-3-run-classification.md 2.7 KB
- references/phase-3-improve-edit-the-agent-file-directly.md 8.4 KB
- references/when-to-use-this-skill.md 1.3 KB
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 · 54 lines · 160 tokens per session scan A b0e975eaf9d5
agentforce-observe is a skill published in the GitHub repository divingsbysangam/salesforce-compound-engineering-plugin (10 stars, last pushed 4d ago), licensed MIT. It adds 160 tokens to every session and 991 once invoked, about $0.0008 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-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…