Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/navapbc/digital-service-orchestra/review-stats)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/review-stats"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/review-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/navapbc/digital-service-orchestra/review-stats"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/review-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 | $0.00817 |
| Opus 5 | $0.00057 | $0.00409 |
| Sonnet 5 | $0.00023 | $0.00163 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
review-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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Stats
Display aggregated statistics from the review event log.
Usage
/dso:review-stats # Stats for the last 30 days (default)
/dso:review-stats --since=2026-03-01 # Stats since a specific date
/dso:review-stats --all # All recorded review events
/dso:review-stats --source=central <subcommand> [options]
# Query central telemetry via query-stats.sh
Arguments
| Flag | Description |
|---|---|
--since=YYYY-MM-DD |
Filter events on or after this date |
--all |
Include all recorded review events (no date filter) |
--source=central |
Route to central telemetry store via query-stats.sh |
Valid --source values: central. Any other value (e.g. --source=bogus, unknown source) is treated as invalid — the agent preserves default local-file behavior and does NOT invoke query-stats.sh.
Execution
Default behavior (no --source flag)
Run the review-stats CLI with any user-provided arguments:
.claude/scripts/dso review-stats.sh $ARGS
where $ARGS are the flags passed by the user (e.g., --since=2026-03-01, --all).
Present the script output to the user as-is.
Important: the default route (no --source flag) does NOT call query-stats.sh. It preserves the existing local-file behavior.
--source=central routing
When the user passes --source=central, dispatch query-stats.sh with the remaining arguments and surface its stdout verbatim:
${CLAUDE_PLUGIN_ROOT}/scripts/telemetry/query-stats.sh <subcommand> [options]
Supported subcommands (passed directly to query-stats.sh):
| Subcommand | Example | Description |
|---|---|---|
roundtrip |
--source=central roundtrip |
Emit test event + poll S3 until it lands |
counts |
--source=central counts --days=7 |
Per-client event counts over N days |
recent |
--source=central recent --days=7 --limit=20 |
Most recent N events |
missing |
--source=central missing --days=30 |
Date-partition gaps in N-day window |
sizes |
--source=central sizes --days=14 |
Per-day object count + total bytes |
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 · 71 lines · 114 tokens per session scan A 66b66bbaa101
review-stats is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 817 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…