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.
npx skills add estuary/agent-skills --skill estuary-task-statsgit clone --depth 1 https://github.com/estuary/agent-skillsWrote 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.
[](https://agentmods.dev/skills/estuary/agent-skills/estuary-task-stats)<a href="https://agentmods.dev/skills/estuary/agent-skills/estuary-task-stats"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/estuary-task-stats/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.
<a href="https://agentmods.dev/skills/estuary/agent-skills/estuary-task-stats"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/estuary-task-stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.01555 |
| Opus 5 | $0.00057 | $0.00777 |
| Sonnet 5 | $0.00023 | $0.00311 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
estuary-task-stats 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flowctl raw stats - Task Processing Statistics
Concepts: Stats show document and byte counts per transaction for a task. They answer "is data actually moving, and how much?" — separate from flowctl catalog status, which only shows control-plane state. A task can show OK status while having zero recent stats (stalled, no new source data, or sync schedule delay).
IMPORTANT: The command is flowctl raw stats, not flowctl stats.
Prerequisites
flowctl must already be authenticated — see the estuary-flowctl-setup skill.
Total Data Over a Period
Materialization — bytes read from source collections ("Data Read" in UI):
flowctl raw stats --task <task> --since 24h | \
jq -s '{
total_gb: ([.[] | select(.materialize != null) | .materialize | to_entries[] | .value.right.bytesTotal // 0] | add // 0 | . / 1073741824 * 10 | round / 10),
total_docs: ([.[] | select(.materialize != null) | .materialize | to_entries[] | .value.right.docsTotal // 0] | add),
transactions: ([.[] | select(.materialize != null)] | length)
}'
Capture — bytes written to Estuary collections ("Data Written" in UI):
flowctl raw stats --task <task> --since 24h | \
jq -s '{
total_gb: ([.[] | select(.capture != null) | .capture | to_entries[] | .value.out.bytesTotal // 0] | add // 0 | . / 1073741824 * 10 | round / 10),
total_docs: ([.[] | select(.capture != null) | .capture | to_entries[] | .value.out.docsTotal // 0] | add),
transactions: ([.[] | select(.capture != null)] | length)
}'
Hourly Breakdown
Useful for spotting gaps, spikes, or batch patterns. Matches the hourly bar chart in the Estuary UI.
Materialization:
flowctl raw stats --task <task> --since 48h | \
jq -s '[.[] | select(.materialize != null) | {
hour: .ts[0:13],
bytes: ([.materialize | to_entries[] | .value.right.bytesTotal // 0] | add),
docs: ([.materialize | to_entries[] | .value.right.docsTotal // 0] | add)
}] | group_by(.hour) | map({
hour: .[0].hour,
gb: (([.[].bytes] | add) / 1073741824 * 10 | round / 10),
docs: ([.[].docs] | add)
})'
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.
- 9d ago First seen · 118 lines · 114 tokens per session scan A 423de6038f76
estuary-task-stats is a skill published in the GitHub repository estuary/agent-skills (7 stars, last pushed 19d ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,555 once invoked, about $0.0006 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.
Other skills, from other repositories
change-data-capture-admin
Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for writing an Apex change-event trigger — use apex/change-data-capture-apex. NOT for subscribing an external system over Pub/Sub or CometD — use…
change-data-capture-admin
Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for CDC Apex trigger implementation (use change-data-capture-integration).
stream-processing-designer
Design a stream processing system for unbounded, continuously arriving data. Use when choosing a message broker (Kafka vs RabbitMQ), implementing change data capture (CDC) from PostgreSQL, MySQL, or MongoDB via Debezium or Maxwell, selecting window types for aggregation (tumbling, hopping, sliding, session), joining…
target-connector
This skill should be used when creating a new target connector for CocoIndex to integrate with external systems. It provides guidance on implementing TargetHandler, TargetActionSink, and related types for declarative target state synchronization with change detection and automatic cleanup.
cocoindex
This skill should be used when building data processing pipelines with CocoIndex, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change…
cocoindex-diagrams
This skill should be used when creating, editing, or reviewing inline SVG diagrams for the CocoIndex docs site (anything under docs/src/content/docs/). It encodes the component-based primitive system under docs/src/components/diagrams/, the palette + shape semantics, the preview-and-verify loop using headless Chrome…