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 5.5 | $0.00046 | $0.00327 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 $0.0005 per session on Opus 5.5. 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.
review-stats compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-statsnavapbc/digital-service-orchestra | Skill | 6 | yesterday | Apache-2.0 | A | 114 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.6k | today | MIT | A | 17 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.4k | today | MIT | A | 49 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 5d ago | MIT | A | 115 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 951 | today | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | today | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | yesterday | MIT | A | 162 | Claude Code, Codex |