agentforce-observe

agentforce-observe is a skill for Claude Code from SalesforceAIResearch/agentforce-adlc. It costs 128 tokens per session (4,573 once invoked), scanned C, original, no licence file.

A skill for examining how Salesforce Agentforce agents behave in production using session traces and Data Cloud records. Agentforce is Salesforce’s platform for building AI agents; session traces are records of agent conversations and actions.

In plain words
What is it for?
Analyzing conversation logs, session data, trace records, and agent performance, and reproducing observed problems.
Why use it?
It helps investigate failures, regressions, and performance issues using recorded production behavior.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agentforce-adlc plugin — 3 skills, 4 agents, 2 hooks shipped together

Good fit Analyzing conversation logs, session data, trace records, and agent performance, and reproducing observed problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/salesforceairesearch/agentforce-adlc/agentforce-observe
Install

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.

Any agent
npx skills add SalesforceAIResearch/agentforce-adlc --skill agentforce-observe
Clone the repo
git clone --depth 1 https://github.com/SalesforceAIResearch/agentforce-adlc

Made for: Claude Code.

Or install agentforce-adlc, the plugin that ships this one along with the rest of its 3 skills, 4 agents, 2 hooks.

Wrote 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.

agentmods badge for agentforce-observe

README.md
[![agentmods](https://agentmods.dev/badge/skills/salesforceairesearch/agentforce-adlc/agentforce-observe/github.svg)](https://agentmods.dev/skills/salesforceairesearch/agentforce-adlc/agentforce-observe)
Your own site
<a href="https://agentmods.dev/skills/salesforceairesearch/agentforce-adlc/agentforce-observe"><img src="https://agentmods.dev/badge/skills/salesforceairesearch/agentforce-adlc/agentforce-observe/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.

agentmods 80×15 button for agentforce-observe

Your own site · 80×15
<a href="https://agentmods.dev/skills/salesforceairesearch/agentforce-adlc/agentforce-observe"><img src="https://agentmods.dev/badge/skills/salesforceairesearch/agentforce-adlc/agentforce-observe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,573 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00128 $0.04573
Opus 5 $0.00064 $0.02286
Sonnet 5 $0.00026 $0.00915
Haiku 4.5 $0.00013 $0.00457

Measured 10d ago against content hash ad51eec65bb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

agentforce-observe scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf force-app/main/default/main
skills/agentforce-observe/SKILL.md · 388 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

7 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.

Changes

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.

  1. 10d ago First seen · 388 lines · 128 tokens per session scan C ad51eec65bb4

Subscribe to this mod's changes

agentforce-observe is a skill published in the GitHub repository SalesforceAIResearch/agentforce-adlc (105 stars, last pushed 1mo ago), with no licence file. It adds 128 tokens to every session and 4,573 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ponytail-audit

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

DietrichGebert/ponytail · 34 tokens

searching-codebases

Binding-resolved Python symbol queries via pyright — every true caller (--refs), the real definition (--def), or an inferred signature (--hover) of a .py symbol, excluding the same-named false positives text search cannot tell apart. Use when a task needs ALL callers or users of a named Python symbol and grep would…

oaustegard/claude-skills · 133 tokens

python-lsp

Semantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need…

oaustegard/claude-skills · 155 tokens

validate-fix

Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.

danielvm-git/bigpowers · 56 tokens

inspect-quality

Interactive QA session where user reports bugs or issues conversationally, and the agent logs them to specs/bugs/registry.yaml with a structured audit schema. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, or mentions "QA session".

danielvm-git/bigpowers · 64 tokens

wire-observability

Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.

danielvm-git/bigpowers · 53 tokens