agentleFS
gokite-aigokite-ai/passport-skills/activity/SKILL.md

activity

Skill2 starsChanged 4 months agoMITView on GitHub

View transaction history and recent account activity. Invoke when the user asks about past spending, wants to verify a payment went through, check if an order completed, review wallet transfers, or see a log of all account actions. Covers wallet transfers, faucet drops, API payments, shopping checkouts, agent registrations, and session approvals.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 3 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prerequisite: Before using any Passport skill, check if kpass is installed by running command -v kpass.

    line 17
  2. Very specific:

    If the user wants to send tokens or check wallet balance, use the wallet-send skill.

    line 36
  3. Very specific:

    If the user wants to execute a payment through a session, use the x402-execute skill.

    line 37
  4. Very specific:

    If the user wants to list agents or sessions, use the manage-agents skill.

    line 38
  5. Very specific:

    If the user wants to search products or checkout, use the shopping skill.

    line 39
  6. Distinctive:

    No agent registration or spending session is required.

    line 45
  7. Distinctive:

    When presenting activity events to the user, format each event as a card:

    line 61
  8. Distinctive:

    Do NOT attempt any of the following.

    line 99
  9. Very specific:

    To send tokens or check balance: Use the wallet-send skill.

    line 114
  10. Very specific:

    To execute API payments: Use the x402-execute skill.

    line 115
  11. Very specific:

    To list agents and sessions: Use the manage-agents skill.

    line 116
  12. Very specific:

    To search products or checkout: Use the shopping skill.

    line 117

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Activity Feed

Prerequisite: Before using any Passport skill, check if kpass is installed by running command -v kpass. If it returns nothing, invoke the passport-setup skill first to install the CLI.

View recent account activity for the authenticated user. Returns a paginated list of activity events including wallet transfers, faucet drops, x402 API payments, agent registrations, session approvals, passkey registrations, and shopping checkouts.

Reference files (read when you need exact detail):

  • @references/commands.md — full command reference, argument table, activity kinds, every JSON output shape, and the input validation checklist.
  • @references/examples.md — worked examples (view all recent activity, filter by kind, paginate).

When to Use This Skill

  • The user asks "show me my recent activity" or "what have I done recently?"
  • The user asks "show me my transaction history" or "what transactions have I made?"
  • The user wants to review spending history or verify a payment went through.
  • The user asks "did my shopping checkout go through?" or "show me my purchases."
  • You need to verify an action was recorded (e.g., confirm a wallet transfer completed).
  • The user asks to filter activity by type (e.g., "show me only my wallet transfers").

When NOT to Use This Skill

  • If the user wants to send tokens or check wallet balance, use the wallet-send skill.
  • If the user wants to execute a payment through a session, use the x402-execute skill.
  • If the user wants to list agents or sessions, use the manage-agents skill.
  • If the user wants to search products or checkout, use the shopping skill.

Prerequisites

The user MUST be authenticated before using this skill. If not logged in (exit code 3 with "Not logged in"), use the authenticate-user skill first.

No agent registration or spending session is required. This command uses the user's JWT directly.

Defaults (Do Not Ask the User Unless They Specify Otherwise)

SettingDefault valueOverride
Output format--output jsonAlways use JSON output. Never omit this flag.
Kind filterOmit (returns all kinds)Only pass --kind when the user asks to filter by activity type.
LimitServer default (20, omit)Only pass --limit if the user requests pagination or you need to limit results.
Offset0 (omit)Only pass --offset for pagination when combined with --limit.
Base URLOmit (uses built-in default)Only pass --base-url if the user explicitly provides a custom backend URL.

Display Cards (MANDATORY)

When presenting activity events to the user, format each event as a card:

For transaction events (wallet_transfer, wallet_faucet, x402_payment — NOT shopping_checkout, which always uses the dedicated template below):

{title} -- {status} Kind: {kind} | {occurred_at} Amount: {details.transaction.amount_raw ÷ 10^details.transaction.decimals} {details.transaction.asset_symbol} | Chain: {details.transaction.chain_name} Tx: {details.transaction.tx_hash}

For shopping checkout events (shopping_checkout):

{title} -- {status} Kind: shopping_checkout | {occurred_at} Items: {details.transaction.shopping.item_count} ({details.transaction.shopping.item_titles joined}) Total: {details.transaction.shopping.total_amount_display} | Order: {details.transaction.shopping.order_id} Tx: {details.transaction.tx_hash}

For non-transaction events (agent_registration, session_approval, passkey_registration):

{title} -- {status} Kind: {kind} | {occurred_at}


Error Handling

Exit CodeMeaningError Message PatternRecovery Action
0Successstatus: "success"Present the result to the user.
1Network errornetwork error: ...Check connectivity. Retry after a brief pause.
2Usage error--limit must be an integer between 1 and 100, --offset must be a non-negative integerFix the flag value. See validation rules in @references/commands.md.
3Auth errorNot logged in. Run ...Use the authenticate-user skill to log in.
5Rate limitedrate limitWait 30 seconds, then retry.
6Session policy violationN/A for activityActivity commands do not use spending sessions. This exit code is not expected.

See @references/commands.md for the exact error envelope of every state.


Commands That DO NOT Exist

Do NOT attempt any of the following. They will fail:

  • kpass activity list -- does not exist; use kpass activity directly
  • kpass activity --type -- the flag is --kind, not --type
  • kpass activity --filter -- does not exist; use --kind
  • kpass transactions -- does not exist; use kpass activity
  • kpass history -- does not exist; use kpass activity
  • kpass activity --status -- does not exist; status is part of the event data, not a filter
  • Any command with --json -- the correct flag is --output json (two separate tokens)

Cross-Skill References

  • Prerequisite: User must be logged in. Use the authenticate-user skill.
  • To send tokens or check balance: Use the wallet-send skill.
  • To execute API payments: Use the x402-execute skill.
  • To list agents and sessions: Use the manage-agents skill.
  • To search products or checkout: Use the shopping skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.