agentmods.dev

activity

A command that summarizes recent non-test activity on the Strale platform, including calls, signups, and x402 activity.

In plain words
What is it for?
Use it to review today’s activity, activity from the last N days, or changes since the previous check.
Why use it?
It gives a short activity snapshot without manually gathering the platform’s separate daily or incremental reports.

Command for Claude Code

4 2d ago A scan 28 tokens original MIT
View the source file strale-io/strale
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.

agentmods
npx agentmods add commands/strale-io/strale/activity
Clone the repo
git clone --depth 1 https://github.com/strale-io/strale

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00028 $0.01061
Opus 5 $0.00014 $0.00531
Sonnet 5 $0.00006 $0.00212
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash a1ba4bd17b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

activity 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 2d 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.

.claude/commands/activity.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/activity — platform activity snapshot

Argument: $ARGUMENTS (empty = today, since-last = incremental, 7d = N days, today = explicit today)

What to do

  1. Pick the right scripts based on the argument, then run them from apps/api/. All scripts need --env-file=../../.env (the root env file, not apps/api/.env):

    • since-last — run only since-last-ext.ts:

      cd apps/api && npx tsx --env-file=../../.env scripts/since-last-ext.ts

      This reads the last-checked timestamp from .claude/state/last-activity-check.json, shows activity since then, and updates the state file. If the user wants a preview without advancing the marker, add --no-update.

    • today or empty — run the three "today" scripts + daily context:

      cd apps/api && npx tsx --env-file=../../.env scripts/today-overview.ts
cd apps/api && npx tsx --env-file=../../.env scripts/today-signups.ts
cd apps/api && npx tsx --env-file=../../.env scripts/today-x402.ts
cd apps/api && npx tsx --env-file=../../.env scripts/daily-ext.ts

      Run them in parallel in a single message.

    • <N>d (e.g. 7d, 3d) — run daily-ext.ts. It defaults to 3 days; for other windows, inline a quick SQL query via a one-off tsx -e or ask the user if they want the script updated.

  2. All queries already exclude internal emails ([email protected], [email protected], [email protected], [email protected]) and status = 'health_probe' rows. Data reflects real external traffic only.

  3. After scripts complete, produce a synthesis — 5 bullets max, covering:

    • Volume: total external calls + completed/failed split
    • Traffic mix: free-tier vs wallet vs x402 vs solutions
    • Signups: count + notable emails/balances
    • Notable patterns: failure bursts, single capability dominating, new users, unusual domains
    • Anything that needs follow-up (e.g. failed_requests spiking → capability gaps)

  4. Then inspect the actual inputs — what emails, URLs, domains, IBANs, etc. are being checked, AND what people searched for on the capability/solutions pages. Run both in parallel:

    cd apps/api && npx tsx --env-file=../../.env scripts/window-inputs.ts <from-iso> <to-iso>
cd apps/api && npx tsx --env-file=../../.env scripts/window-searches.ts <from-iso> <to-iso>
    • For since-last: use the window boundaries printed by since-last-ext.ts (from → to).
    • For today: use start-of-day CET to now.
    • For <N>d: use N days ago to now.

Read the full file on GitHub · 61 lines

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. 2d ago First seen · 61 lines · 28 tokens per session scan A a1ba4bd17b07

Subscribe to this mod's changes

activity is a command published in the GitHub repository strale-io/strale (4 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 1,061 once invoked, about $0.0001 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.

Backend and APIsCode reviewTestingai-agentsapieu-ai-actmcpqualitytrust
Related

Other commands, from other repositories

sonicjs-seo-blog

Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.

SonicJs-Org/sonicjs · 0 tokens

create-pr

Create a pull request following the official template.

rootstrap/rails_api_base · 0 tokens

templates

Manage locally-stored email templates for composing messages with variable substitution.

nylas/cli · 0 tokens

cli-patterns

Reference patterns for implementing CLI commands in internal/cli/.

nylas/cli · 0 tokens

docguard.update

Update canonical docs after code changes — detect drift and sync documentation.

raccioly/docguard · 12 tokens

encryption

Encrypt outgoing emails with GPG/PGP so only the intended recipient can read them.

nylas/cli · 0 tokens