Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts.

Custom licenceAuto-check: notesDevOps & Cloud

Install Agentforce Observe

skills CLI
$ npx skills add SalesforceAIResearch/agentforce-adlc --skill agentforce-observe -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install SalesforceAIResearch/agentforce-adlc agentforce-observe --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/SalesforceAIResearch/agentforce-adlc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agentforce-observe .claude/skills/agentforce-observe && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agentforce-observe
GitHub stars
114
Used in
1 other repo
Token cost
~5.6k tokens
SKILL.md length
2,072 words
Files
9 (incl. references, assets)
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts.

  • Works in 5 steps: Discover Data Space → ALT: Observe Without STDM (Fallback Path) → Observe -- Query STDM → …
  • : user queries STDM session data
  • SKILL.md covers Platform Notes, Routing, Phase 0: Discover Data Space and Phase 1-ALT: Observe Without…, plus 3 more sections
  • Calls sf, jq and python3

What it does

Agentforce Observe is an agent skill from SalesforceAIResearch/agentforce-adlc. Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries; creates, lists, updates, or deletes an AHM data alert on an agent…

Its SKILL.md is about 5.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files and assets (for example `references/ahm-alerts.md`, `references/improve-reference.md` and `references/issue-classification.md`).

It sits in DevOps & Cloud. It works with Python. The repository describes itself as: Agent Development Life Cycle — Build, deploy, test, and optimize Agentforce agents using Claude Code skills and Agent Script DSL.

When your agent uses it

  • : user queries STDM session data
  • Data Cloud trace records
  • Investigates production agent failures
  • Performance issues

Example prompts

  • “/agentforce-observe”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Discover Data Space
  2. ALT: Observe Without STDM (Fallback Path)
  3. Observe -- Query STDM
  4. Reproduce -- Live Preview
  5. Improve -- Edit .agent File Directly

What it can do on your machine

Read from SKILL.md and the folder at commit 09bf153. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit
    • Glob
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • sf
    • jq
    • python3
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agentforce Observe loads about 5.6k tokens when it runs, and up to ~35k if it reads all its reference files. Until then it costs about 239 tokens; SKILL.md has 2,072 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~239
When it runs · the whole SKILL.md, loaded when a task matches
~5.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~35k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit, Glob, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,072 words (~5,620 tokens).

“Improve Agentforce agents using session trace data and live preview testing.”

— opening of SKILL.md by SalesforceAIResearch, Custom licence
name
agentforce-observe
allowed-tools
Bash, Read, Write, Edit, Glob, Grep
metadata.relatedSkills
agentforce-generate, agentforce-test
metadata.version
0.9
metadata.domains
Agentforce, Data 360

Read the full SKILL.md on GitHub

Files

SKILL.md and 8 other files (references, assets) in skills/agentforce-observe of SalesforceAIResearch/agentforce-adlc.

  • SKILL.md
  • assets/apex/AgentforceOptimizeService.cls
  • assets/apex/AgentforceOptimizeService.cls-meta.xml
  • references/ahm-alerts.md
  • references/improve-reference.md
  • references/issue-classification.md
  • references/reproduce-reference.md
  • references/stdm-queries.md
  • references/stdm-schema.md

Open the folder on GitHubat commit 09bf153

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in SalesforceAIResearch/agentforce-adlc, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Agentforce Observe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agentforce Observe compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agentforce Observe this skillSalesforceAIResearch/agentforce-adlc1141 repos~5.6kAutomated safety check: NotesCustom licence
AWS Cdk Developmentzxkane/aws-skills3672 repos~2.5kAutomated safety check: PassMIT
Reproduce macOS Python FlavorsNuitka/Nuitka15k—~1.7kAutomated safety check: PassAGPL-3.0
Env Var Conventionssgl-project/sglang37k2 repos~2.9kAutomated safety check: PassApache-2.0
Pymobiledevice3 Device Operatordoronz88/pymobiledevice32.9k—~1.8kAutomated safety check: NotesGPL-3.0
Vetatilladeniz/Kubeli3872 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • AWS Cdk Development

    zxkane/aws-skills

    AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python.

    367 GitHub starsUsed in 2 repos~2.5k tokens
    DevOps & CloudAuto-check passed
  • Reproduce macOS Nuitka issues across Python distributions and GitHub Actions Python packaging.

    15k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Env Var Conventions

    sgl-project/sglang

    Conventions for SGLang environment variables — where to define, how to access, how to name, and how to deprecate.

    37k GitHub starsUsed in 2 repos~2.9k tokens
    DevOps & CloudAuto-check passed
  • Pymobiledevice3 Device Operator

    doronz88/pymobiledevice3

    Operate iOS and iPadOS devices with pymobiledevice3, from a local checkout or straight from PyPI via uvx on a fresh workstation.

    2.9k GitHub stars~1.8k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Vet

    atilladeniz/Kubeli

    Run vet immediately after ANY logical unit of code changes. An agent skill from atilladeniz/Kubeli.

    387 GitHub starsUsed in 2 repos~1.6k tokens
    DevOps & CloudAuto-check passed
  • Statem

    henryqin1997/statem

    A skill your agent uses when a long coding or research task should be managed with statem state-machine runbooks, including creating specs, starting or resuming runs, checking current state…

    1.3k GitHub stars~1.2k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

More from SalesforceAIResearch/agentforce-adlc

  • Agentforce Generate

    SalesforceAIResearch/agentforce-adlc

    Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.

    114 GitHub starsUsed in 1 repo~7.4k tokens
    Auto-check passed

Works with

Categories

Questions about Agentforce Observe

What does Agentforce Observe do?

Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. Agentforce Observe is an agent skill from SalesforceAIResearch/agentforce-adlc. Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts.

When should I use Agentforce Observe?

Agentforce Observe fits situations like: : user queries STDM session data; data Cloud trace records; investigates production agent failures; performance issues.

How do I install Agentforce Observe in Claude Code?

Run `npx skills add SalesforceAIResearch/agentforce-adlc --skill agentforce-observe -a claude-code`. Or copy the skill folder (skills/agentforce-observe in SalesforceAIResearch/agentforce-adlc) into .claude/skills/agentforce-observe in your project. Claude Code loads it when a task matches its description.

How do I install Agentforce Observe in Codex?

Run `npx skills add SalesforceAIResearch/agentforce-adlc --skill agentforce-observe -a codex`. Or copy the skill folder (skills/agentforce-observe in SalesforceAIResearch/agentforce-adlc) into .agents/skills/agentforce-observe in your project. Codex loads it when a task matches its description.

Can I use Agentforce Observe in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SalesforceAIResearch/agentforce-adlc --skill agentforce-observe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentforce-observe, .gemini/skills/agentforce-observe, .github/skills/agentforce-observe and .opencode/skills/agentforce-observe in your project.

What does Agentforce Observe need to run?

Going by SKILL.md and its folder, Agentforce Observe needs the command-line tools its instructions call (sf, jq, python3 and python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Glob, Grep.

Does Agentforce Observe access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agentforce Observe safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Agentforce Observe use?

Agentforce Observe has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Agentforce Observe use?

About 5.6k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 30k tokens, read only when the agent opens those files.

What are the alternatives to Agentforce Observe?

Skills that share tags, products or a category with Agentforce Observe: AWS Cdk Development (zxkane/aws-skills, 367 stars), Reproduce macOS Python Flavors (Nuitka/Nuitka, 15k stars), Env Var Conventions (sgl-project/sglang, 37k stars) and Pymobiledevice3 Device Operator (doronz88/pymobiledevice3, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agentforce Observe?

SalesforceAIResearch (a GitHub organization) maintains it in SalesforceAIResearch/agentforce-adlc, which has 114 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 12, 2026.

Source: SalesforceAIResearch/agentforce-adlc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.