Sashiko is an automated code-review system specialized for proposed Linux kernel changes. Kernel maintainers and developers use it to inspect patches from mailing lists or local Git repositories with Linux-specific review instructions and language models. The catalogue add-ons provide its agent workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sashiko-dev/sashiko --skill review-prgit clone --depth 1 https://github.com/sashiko-dev/sashikoWrote 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/sashiko-dev/sashiko/review-pr)<a href="https://agentmods.dev/skills/sashiko-dev/sashiko/review-pr"><img src="https://agentmods.dev/badge/skills/sashiko-dev/sashiko/review-pr.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00730 |
| Opus 5 | $0.00033 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
review-pr 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 7d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR Skill
Core Directives
When asked to perform a code review, follow these steps strictly:
1. Context Gathering & Design Detection
- Read Baseline Standards: Immediately read
GEMINI.md(or the equivalent local project standard file) to establish the coding standards, style guidelines, and mandatory architectural rules. - Analyze Code Scope: Look at the files modified in the PR or the specific code components requested for review. Identify the core features or modules being touched (e.g.,
cli,auth,db). - Detect Design Documents: Automatically locate the project's design directory. Look for directories named
designs/,docs/design/,rfcs/, orarchitecture/. - Map and Read Design Docs: Map the modified files/modules to specific design documents. For example, if
sashiko-cli.rsis modified, look for a file likeDESIGN_CLI_TOOL.md. Read the matched design documents to understand the intended architecture and behavior.
2. Analysis
Perform a deep, scrutinizing code review of the target code against the gathered context. Evaluate for:
- Design Alignment: Does the implementation match the intent described in the design documents?
- Safety & Security: Are there any risky operations (e.g., unchecked unwraps, poor error handling, thread safety issues, SQL injection risks, insecure dependency usage, or credential leakage)?
- Regression Analysis: Assess if the changes could break existing functionality. Check for impacts on related modules, performance regressions, or unintended side effects in shared components.
- Idiomatic Conventions: Does the code use the language idiomatic patterns and the project-specific coding standards defined in
GEMINI.md? - SOLID/DRY Principles: Reference references/principles.md and evaluate the code for adherence to SOLID and DRY principles within the Rust context.
- Test Coverage: Are unit or integration tests missing for new logic?
3. Reporting
Output your findings in a structured, categorized markdown format. Use the following emoji prefixes for each finding to indicate severity/type:
- 🔴 Safety / Bugs / Security: Broken behavior, potential crashes, security risks, or unhandled errors.
- 🟠 Regressions: Potential to break existing functionality or introduce performance bottlenecks.
- 🟡 Complexity / Logic / SOLID: High cyclomatic complexity, functions that are too long, risky architectural choices, or violations of SOLID principles.
- 🔵 Style / Nits / DRY: Style violations, naming issues, duplicated code (DRY violations), or minor optimizations.
- 🟢 Design Alignment: Noting where the code successfully or unsuccessfully aligns with the mapped design documents.
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.
- 7d ago First seen · 40 lines · 66 tokens per session scan A 4f27a95992d0
review-pr is a skill published in the GitHub repository sashiko-dev/sashiko (1,212 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 730 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.