Index of every page on this site: llms.txt
All skills
n8n-io avatar

/instance-awareness

@273d130 official
by n8n - Workflow Automationn8n-io/n8n211k stars
61,599
Run it yourself

Load when the request depends on what is already on this instance rather than on what the user just typed: a short or ambiguous opener ("fix it", "carry on", "what should I look at"), a reference to earlier work in a new conversation, or any question about what has recently run or broken.

Use this Skill: https://skilld.dev/gh/n8n-io/n8n/instance-awareness

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈77 tokens for metadata: the name and description. ≈1.3k when used: this file.

Description uses 3.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈310 characters, or 3.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Instance Awareness

The conversation is not the only context you have. This instance carries a record of what has been built, changed, run and broken. Most of it is cheap to read, and reading it is usually better than asking.

The one rule

Ask about intent. Look up state.

What the user wants next is theirs to tell you. What already exists here is yours to find out. A question you could have answered by looking costs the user a turn and tells them you are not paying attention — and it is the most common complaint in reviewed conversations: the assistant re-asking for something it had, or restarting work it had already finished.

Read in this order — cheapest first

Each rung answers a narrower question at a higher cost. Stop at the first one that answers yours. Do not start at the bottom.

0. The block you were already given

If an <instance-context> block is in this turn, you already have three things for free: which workflows exist here, what changed recently, and what has run or failed. Read it before your first tool call.

It is a set of pointers, not contents. Each change line ends with the resource it is about, and the bracketed number is a stable id. Run lines carry the execution id of the last failure, which is what get_execution and debug_execution take.

A later turn may bring a shorter block that says it is an addition. Those are extra entries, not a replacement — the earlier ones still stand.

1. activity(action="list") and activity(action="expand", id=N)

list looks further back than the block, or filters to one category or one resource. expand opens a single entry in full and returns up to 20 more recent entries for the same resource — which is how you see a workflow's recent change history in a single call. Twenty is a cap, not a total: an older history continues past it, and list with that resourceId reads further back.

Use expand when a line is interesting but thin: a save you want the detail of, or a workflow you want the history of. An id that no longer resolves is ordinary — entries are pruned — so carry on rather than treating it as an error.

The log covers workflow and credential changes. It does not record runs; those come from the block, and get_execution has the detail.

2. One workflow, read in full

get_workflow(workflowId, full=true) on one example — the one the block points at, or the one the user named. This rung is for what an entry cannot express: parameter values, naming, retry settings, error-workflow wiring, how a prompt is structured.

Pass full=true. Without it a large workflow comes back as structure only, with its node parameters omitted — which is exactly what this rung is for.

Read one, not several. If one example is not enough to see the pattern, there is probably no pattern to follow.

What each surface can and cannot tell you

Question Where it is answered
What already exists here? the block, rung 0
What did they just change? the block, rung 0
Which workflow do they mean by "it"? the block — the most recent one they touched
What is broken right now? the block's run lines, then debug_execution for the detail
Did the nightly job run? the block, then list_executions
Who changed this, and was it me? activity(action="expand") — entries carry provenance
How do they configure it? one workflow, rung 2
Do they have a credential for X? list_credentials

Resolving a vague opener

"fix it", "carry on", "why is this broken", "what should I look at", or a new conversation about work from yesterday: the answer is nearly always the most recent thing in the block, and usually the most recent failure.

Name what you think they mean and act on it — "picking up the stale-issue nudge workflow, which failed twice this morning" — rather than asking them to choose from a list they can already see. If two candidates are equally recent, that is when to ask, and ask with the candidates named.

Reusing what they changed by hand

A save entry records which node types were added or removed, and whether the change came from the assistant or from the user. A change the user made by hand to something you built is a preference worth honouring: reuse it if it is a small tweak, and ask before overriding it if it conflicts with what you were about to do.

Where this stops

  • An entry is not the workflow. It records that a save happened and which node types moved, never the parameters. Anything about contents is rung 2.
  • An entry can outlive its resource. A deletion entry points at a workflow that is gone; that is the entry doing its job.
  • Runs end where retention ends. The instance keeps executions for a bounded window, so an older failure may be gone even though the workflow is not.
  • Recent is not the same as typical. The newest workflow may be the odd one out.
  • Do not narrate the block. It is context for reading intent, not a status report. Unless the user asked what has been happening, let it change what you do rather than what you say.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill provides instructions for the agent to gain context about the current n8n instance, such as recent activity, workflows, and executions. While useful for streamlining user requests, it introduces an indirect prompt injection surface by encouraging the agent to derive intent from potentially user-controlled resource metadata without specific sanitization guidelines.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 273d130. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
recommended_tool_groups
[
  "workflows",
  "executions",
  "credentials"
]

README badge

README badge for n8n-io/n8n/instance-awareness