review-program
/review-program
ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.
- Author
- PolicyEngine ↗
- Repository
- policyengine-claude ↗
- Licence
- MIT
- Last repository change
- 19.10.2026
Assessment and security
- Files in this package
- 10
- Scripts
- 4
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 19.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 4 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/assemble_review.py, scripts/check_source_manifest.py, scripts/review_diagnostics.py, scripts/run_bounded.py
What it does and when to use it
ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.
Original author description
ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.
How it works
SKILL.md has no level-two headings · 68 lines, 515 words
SKILL.md preview
---
name: review-program
description: ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.
metadata:
category: workflows
---
# review-program
Thin launcher. The canonical workflow — phases, roles, gates, severity rules, artifact
contracts — lives in [references/workflow.md](references/workflow.md). Read it completely
before acting and follow it exactly; this file only adapts it to this surface. Do not
redefine flags, phases, severity rules, file ownership, or completion gates here.
Use this skill for PolicyEngine-specific PR reviews even when the user starts from a
generic built-in review command (such as Codex `/review`): the canonical workflow adds
PolicyEngine source, reference, regulatory, PDF, and test-review rules a generic review
lacks.
Treat the text after `$review-program` or `/review` as the raw workflow arguments:
```text
$review-program [PR_NUMBER_OR_SEARCH] [PDF_URL] [--local] [--local-diff] [--full]
[--skip-pdf] [--600dpi] [--resume] [--incremental REPORT] [--prefix NAME]
[--sources MANIFEST] [--source-budget MINUTES]
```
With `--local-diff`, the PR argument may be omitted for unpublished local work; the
canonical workflow resolves the base repository and reviews local HEAD without a PR.
Mandatory completion gate:
- Default to policy/source and code/test reviewers; consolidate their findings directly.
- Reviewers do their own investigation and never delegate helper or verification tasks.
Use the surface adapter's reviewer profile; read-only model work still requires skills.
- Reviewers own finding validation. The coordinator resolves specific conflicts and
assembles the result; calling workflows route repairs without reviewing it again.
- For country-model work, the coordinator and each reviewer load model-development in
their own contexts before substantive work and supply the canonical loading evidence.
- The review is incomplete until `{RUN_ROOT}/{PREFIX}-review-full-report.md` and
`{RUN_ROOT}/{PREFIX}-review-summary.md` exist, with
`{RUN_ROOT}/{PREFIX}-review-result.json` for confirmed-critical repair dispatch.
- Phase 6 consolidation is required before displaying or posting findings.
- Report COMPLETE or PARTIAL separately from the critical count; missing material
evidence cannot be reported as a clean review.
Surface adapters:
- **Claude Code**: also read
[references/claude-launcher.md](references/claude-launcher.md) — it maps canonical
roles to this plugin's agent types and the workflow's abstract operations to Claude
Code mechanics.
- **Codex**: use the delegation mapping below.
Delegation mapping (when subagent use is available and authorized):
- Map the two substantive reviewer roles to workers with skill access. Where supported,
remove delegation tools from those workers. They perform read-only dependency tracing
themselves rather than creating additional explorers or reviewers.
- Pass concrete `RUN_ROOT`, `WORKTREE_ID`, `PREFIX`, and (from Phase 1) `SNAPSHOT`
values and the role's task spec from the canonical workflow to every subagent; name
the role's skills explicitly in the subagent prompt — do not assume a worker infers
them from parent context.
- For country-model work, each worker resolves model-development in its own runtime
catalog, reads the full entrypoint with its catalog-specified access mechanism and
supplies the canonical `SKILLS_READY` evidence. Missing skill availability/load is a
blocker, not a reason to silently substitute repository excerpts.
- Every subagent appends progress lines to its canonical progress log while working and
finishes by writing its assigned file and returning the one-line DONE message from the
canonical completion contract. Dispatch reviewers before writing the scope brief when
the runtime can message a running worker; otherwise include a brief capped at one minute.
- If subagents are unavailable or not authorized, execute the roles directly in phase
order, preserving the same handoff files and read-only contract.
Files in this package (10)
- SKILL.md 4 KB
- references/automation.md 8 KB
- references/benchmark.md 12 KB
- references/claude-launcher.md 5 KB
- references/source-cache.md 3 KB
- references/workflow.md 39 KB
- scripts/assemble_review.py 13 KB
- scripts/check_source_manifest.py 5 KB
- scripts/review_diagnostics.py 7 KB
- scripts/run_bounded.py 2 KB
Versions
The database has no other skills named review-program.
Database snapshot: 13.11.2026 · package version b2f2e3c5d8d0 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 96fix-pr
Use when the user invokes $fix-pr or asks Codex or Claude Code to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures, or local review reports. - 96encode-policy-v2
Use when the user invokes $encode-policy-v2 or asks Codex or Claude Code to implement a new PolicyEngine-US state benefit program or a new structural program component from official rules. Covers existing-program routing, source collection and selective PDF inspection,… - 100pr-comment-review
This skill should be used when the user asks to review a GitHub pull request AND post the findings as a comment on the PR ('review and comment on PR', 'review PR roi comment len do'). Multi-agent confidence scoring, threshold 80/100, posts via gh. For local working-tree review… - 96code-review
This skill should be used when the user asks to code-review a GitHub pull request ('review PR #123', 'code review this pull request') with multi-agent confidence-scored analysis; pass --comment to post findings as inline comments on the PR. For reviewing local uncommitted… - 95pr-review
Reviews pull requests with scope validation, requirements compliance, and line comments. Use when reviewing GitHub or GitLab PRs. - 100gh-pr-review
Reviews GitHub PRs with multi-agent orchestration for comprehensive validation. Triggers on keywords: PR review, review PR, GitHub PR review, pull request review