agentmods.dev

dakota: Skill for Claude Code

.agents/skills/dakota-review/SKILL.md

dakota-review is a skill for Claude Code, Codex from projectbluefin/dakota. It costs 24 tokens per session (875 once invoked), scanned A, original, MIT.

A review guide for Dakota pull requests and related issues. A pull request is a proposed code change awaiting review; the guide also covers contributor reports, labels, and hardware verification evidence.

In plain words
What is it for?
Use it to review pull requests, inspect checks, handle scoped issues, read attached reports, apply labels, or assess post-release hardware confirmation.
Why use it?
It gives reviewers a consistent way to check the target branch, scope, required tests, ownership, and real-device evidence before approving or closing work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is projectbluefin/dakota's own configuration. It tells Claude Code and Codex how to work on dakota itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dakota configures →

not rated 151repo +2 changed 2d ago A scan SkillSpector: pass 24 tokens original MIT
View source ↗ projectbluefin/dakota projectbluefin.io
Reuse

Borrowing it

Nothing to install: this file belongs to projectbluefin/dakota. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/projectbluefin/dakota/testing/.agents/skills/dakota-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/projectbluefin/dakota

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for dakota-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-review/github.svg)](https://agentmods.dev/skills/projectbluefin/dakota/dakota-review)
Your own site
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-review"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-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.

agentmods 80×15 button for dakota-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-review"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00875
Opus 5 $0.00012 $0.00438
Sonnet 5 $0.00005 $0.00175
Haiku 4.5 $0.00002 $0.00088

Measured 2d ago against content hash d90e2a14ad24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dakota-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 2d 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.

.agents/skills/dakota-review/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dakota Review and Issue Workflow

Review pull requests and issues with high discipline: minimal diff, correct target branch, evidence-based verification, and strict boundaries.

When to Use

  • Performing code or architecture reviews on PRs in projectbluefin/dakota
  • Triaging issues, user-donated diagnostic gists (ujust report), or verification comments
  • Enforcing contributor guidelines, PR checklists, and commit hygiene

When NOT to Use

  • Writing code changes or authoring elements → load dakota-buildstream or dakota-packaging
  • Modifying release promotion or signing gates → load dakota-release
  • Authoring CI workflows → load dakota-ci

Core Process

  1. Verify Target Branch: Ensure PR targets testing (or next if explicitly tracking rolling), never main.
  2. Review Hygiene & Commits:
    • Check commit format: <type>(<scope>): <description>.
    • Ensure commits use Assisted-by:, never Co-authored-by:.
  3. Inspect Implementation:
    • Ensure image changes use BuildStream elements (no DNF, RPMs, or Containerfiles).
    • Ensure layer additions use kind: compose (never kind: stack).
    • Check that third-party GitHub Actions are pinned to full commit SHAs.
  4. Evaluate Evidence:
    • For bugs, check for attached gists from ujust report.
    • Verify that claimed test results were actually executed (just validate, just boot-test, etc.).
  5. Constructive Feedback:
    • If asked to post feedback, compose at most one concise, actionable comment.
    • Never restate GitHub UI status (e.g. "checks are passing").

Invariants

  • PROHIBITION ON ublue-os/*: Never write to any ublue-os/* repository under any circumstance. Ask a human to report upstream manually.
  • Commit Trailer Invariant: Use Assisted-by:, never Co-authored-by:.
  • Target Branch: PRs must target testing. main is a release bookmark.
  • Hardware Evidence Priority: verified: N/3 on issues is post-ship proof that cannot be substituted by CI. Do not close bugs without hardware verification or explicit maintainer direction.
  • Communication Etiquette: Do not post automated comments or review messages unless explicitly commanded by the user.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 2d ago Changed · +19 lines d90e2a14ad24
  2. 11d ago First seen · 58 lines · 24 tokens per session scan A 46b1f603831b

Subscribe to this mod's changes

dakota-review is a skill published in the GitHub repository projectbluefin/dakota (151 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 875 once invoked, about $0.0001 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.

Code reviewHardware and IoT
Related

Other skills, from other repositories

kicad-pcb-review

Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.

oaslananka/kicad-mcp-pro · 31 tokens

arch-review

Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.

babyworm/rtl-agent-team · 35 tokens

cdc-tool-profiles

Internal reference: cdc tool profiles (agent-loaded; do not invoke).

babyworm/rtl-agent-team · 20 tokens

rtl-review

Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.

vibeic/vibe-ic · 63 tokens

kicad-pcb-review

KiCad PCB review and manufacturing readiness agent skill for Cursor.

oaslananka/kicad-mcp-pro · 19 tokens

code-review-policy

Internal reference: code review policy (agent-loaded; do not invoke).

babyworm/rtl-agent-team · 18 tokens