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/plan-review)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/plan-review"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/plan-review/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/plan-review"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/plan-review.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 | $0.00140 | $0.01323 |
| Opus 5 | $0.00070 | $0.00661 |
| Sonnet 5 | $0.00028 | $0.00265 |
| Haiku 4.5 | $0.00014 | $0.00132 |
Grade A, and why
plan-review 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 8d 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.
Plan Review
Orchestrator-level skill that dispatches a dso:plan-review sub-agent to review plans and designs before the user sees them. This skill runs at the orchestrator level — it is NOT itself dispatched as a sub-agent (the SUB-AGENT-GUARD above enforces this).
When to Invoke
MANDATORY before any of these:
- Presenting a design doc to the user for approval (brainstorming skill)
- Presenting an implementation plan to the user (writing-plans skill)
- Calling
ExitPlanMode(plan mode)
The hook on ExitPlanMode enforces this mechanically. For brainstorming and writing-plans, this is skill-enforced.
Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
artifact_type |
Yes | — | "design" or "implementation_plan" |
artifact_path |
Yes | — | Path to the plan/design file, or inline content |
Process
Step 1: Dispatch Review Sub-Agent
Launch a single sub-agent with the plan content and review rubric.
Model selection:
artifact_type: "design"→opus(architectural reasoning)artifact_type: "implementation_plan"→sonnet(structural analysis)
Sub-agent prompt: Read and fill placeholders in ${CLAUDE_PLUGIN_ROOT}/docs/workflows/prompts/plan-review-dispatch.md. Replace {artifact_type} and {artifact content} with actual values.
Inline dispatch is required — dso:plan-review is an agent file identifier, NOT a valid subagent_type value. The Agent tool only accepts built-in types (general-purpose, Explore, Plan, etc.). Read agents/plan-review.md inline and dispatch as subagent_type: "general-purpose" with the model below.
Launch with:
Agent tool:
subagent_type: "general-purpose"
model: opus (design) or sonnet (implementation_plan)
# Model rationale: design needs trade-off reasoning across architectural
# coherence (opus); implementation_plan needs structured analysis of task
# atomicity / dependency graph / TDD discipline (sonnet — haiku misses
# implicit coupling).
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.
- 8d ago First seen · 118 lines · 140 tokens per session scan A e131c233c875
plan-review is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 140 tokens to every session and 1,323 once invoked, about $0.0007 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…