Borrowing it
Nothing to install: this file belongs to hiero-ledger/solo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hiero-ledger/solo/main/.claude/skills/solo-pr-review/SKILL.mdgit clone --depth 1 https://github.com/hiero-ledger/soloWrote 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/hiero-ledger/solo/solo-pr-review)<a href="https://agentmods.dev/skills/hiero-ledger/solo/solo-pr-review"><img src="https://agentmods.dev/badge/skills/hiero-ledger/solo/solo-pr-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/hiero-ledger/solo/solo-pr-review"><img src="https://agentmods.dev/badge/skills/hiero-ledger/solo/solo-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00143 | $0.03825 |
| Opus 5.5 | $0.00057 | $0.01530 |
| Sonnet 5.5 | $0.00029 | $0.00765 |
| Haiku 4.5 | $0.00014 | $0.00382 |
Grade A, and why
solo-pr-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 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solo PR Review
Review pull requests in hiero-ledger/solo the way the Solo Team reviews them. This skill encodes the conventions
enforced repeatedly across the project so reviews stay consistent whether they're authored by a human or generated here.
When to use
- The user supplies a PR number, PR URL, branch name, commit range, or file list and asks for a review.
- The user asks "what would you flag in this change?", "review my branch", or similar.
- The user is the PR author preparing to push and wants a self-review pass.
Do not use for: greenfield architecture proposals (use architecture-designer), security-only audits (use
security-review), or generic non-Solo TypeScript reviews (use code-reviewer).
Required reading before reviewing
Open these before writing any feedback. They are the rulebook — the review must cite them when something is off.
| File | What it owns |
|---|---|
docs/contributing/typescript-code-style.md |
The full TS style guide (DRY/SOLID, naming, imports, types, etc.) |
CLAUDE.md |
Project-level conventions and gotchas (flags, env vars, etc.) |
eslint.config.mjs |
Enforced lint rules (errors, not warnings) |
.prettierrc.json |
Formatting (120 col, single quotes, etc.) |
Core workflow
- Establish intent. Read the PR description (and any linked issue) and state the goal in one sentence. If the goal is unclear, stop and ask the author — do not guess.
- Inventory the diff. List every file changed and group them: source, tests, workflows, docs, examples, generated. Note the size of each group. Big diffs that touch many groups warrant a structural pass before a line pass.
- Structural pass. Walk the checklist in
references/solo-review-checklist.md. This catches the recurring issues ( DRY violations, exported functions, generic-flag wording, error-handling drift, missing Windows support, etc.) before getting into line-by-line nits. - Line pass. Read the actual diff. For each finding, decide:
- Critical — bug, security issue, data loss, broken backwards compatibility, build/CI break.
- Major — design/architecture issue, DRY/SOLID violation, missing default behavior, cross-platform regression, drift from existing patterns.
- Minor — naming, comment hygiene, suggestion-block one-liners.
- Question — something that looks off but might have a reason. Ask before claiming.
- Comment-to-implementation pass. For every changed behavioral comment, JSDoc, test name/comment, example, documentation claim, and PR-description assertion, trace the claim to the final source and test behavior. Confirm that APIs, control flow, process boundaries, logging, configuration propagation, and claimed coverage are exactly what the text says. Treat wording left over from an earlier commit or implementation as a finding — not as reliable context — and distinguish a documentation-only mismatch from behavior that is actually broken or concealed by the stale wording.
- Test pass. Are there tests? Are they unit (cheap, fast) or did the author reach for E2E/nightly when a unit test would do? Do the tests execute the behavior their names and the PR description claim they cover? Flag missing or overstated unit coverage explicitly.
- Verification ledger. Before writing anything, tag every Critical and Major with the evidence actually behind it:
- executed — you ran a command and read its output. Quote the load-bearing lines in the finding itself.
- read-in-full — you read the entire file, issue, or rule the claim depends on.
- inferred — you reasoned from the diff without running or fully reading anything.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +47 lines 72f88a657dfb
- 2mo ago First seen · 246 lines · 143 tokens per session scan A 857c0382f3b1
solo-pr-review is a skill published in the GitHub repository hiero-ledger/solo (45 stars, last pushed yesterday), licensed Apache-2.0. It adds 143 tokens to every session and 3,825 once invoked, about $0.0006 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 2026-09-01.
solo-pr-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| solo-pr-reviewhiero-ledger/solo | Skill | 45 | yesterday | Apache-2.0 | A | 143 | Claude Code |
| code-reviewgithub/awesome-copilot | Skill | 41k | yesterday | MIT | A | 27 | Claude Code, Codex |
| code-changesJanDeDobbeleer/oh-my-posh | Skill | 24k | 2d ago | MIT | A | 48 | Claude Code, Codex |
| clean-abapmarcellourbani/vscode_abap_remote_fs | Skill | 406 | 3d ago | MIT | A | 73 | Claude Code |
| abap-code-review-helpermarcellourbani/vscode_abap_remote_fs | Skill | 406 | 3d ago | MIT | A | 142 | Claude Code, Codex |
| repository-assisted-applymarcellourbani/vscode_abap_remote_fs | Skill | 406 | 3d ago | MIT | A | 57 | Claude Code, Codex |
| oss-find-real-issueschiruu12/OSS-Skills | Skill | 62 | 2mo ago | MIT | A | 80 | Claude Code, Codex |