dakota: Skill for Claude Code

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

dakota-ci is a skill for Claude Code, Codex from projectbluefin/dakota. It costs 29 tokens per session (886 once invoked), scanned A, original, MIT.

A skill for diagnosing and changing Dakota CI workflows, which automate Dakota's validation, builds, publishing, remote execution, and end-to-end tests.

In plain words
What is it for?
Use it to investigate failed pipeline runs, validate graph and image builds, check architecture-specific builds and boots, publish images, and maintain release workflows.
Why use it?
It helps locate whether a failure comes from the workflow, source retrieval, build system, artifact transfer, publication, or tests before changes are made.

Skill for Claude CodeCodex

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

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 →

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-ci/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-ci

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-ci"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 886 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 $0.00029 $0.00886
Opus 5 $0.00015 $0.00443
Sonnet 5 $0.00006 $0.00177
Haiku 4.5 $0.00003 $0.00089

Measured 2d ago against content hash 80b145e6e1f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dakota-ci 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-ci/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dakota CI

Workflow YAML in .github/workflows/ is the current source of truth. Do not rely on historical runbooks when the workflow says something different.

When to Use

  • Modifying or debugging GitHub Actions workflows in .github/workflows/
  • Diagnosing runner startup, syntax, matrix, or permission failures
  • Changing build, publish, or validation triggers and artifact flows
  • Investigating remote CAS caching or remote execution integration

When NOT to Use

  • Stable promotion, image signing, cosign attestation, or rollback → load dakota-release
  • BST element syntax or internal build errors → load dakota-buildstream
  • Reviewing PRs and issue management → load dakota-review

Core Process

  1. Route the Workflow: Identify the failing workflow:
    • validate.yml: PR graph checks and patch drift
    • build.yml / build-aarch64.yml: Remote execution x86/ARM builds into CAS
    • publish.yml: CAS artifact checkout, squashing, tagging, signing
    • e2e.yml: Manual testsuite dispatch against published images
  2. Inspect at Run SHA: Read the workflow YAML at the exact commit that executed.
  3. Isolate Root Cause: Distinguish syntax/permission failure (zero jobs run), source fetch failure, remote CAS cache failure, or BST compilation error.
  4. Enforce Least Privilege: Ensure workflow caller permissions strictly match what reusable workflows demand.
  5. Validate Locally: Run just check-publish-workflow and just validate before submitting.

Invariants

  • Third-Party Actions: Pin all third-party actions to full 40-character commit SHAs with an inline version comment. projectbluefin/actions@v1 is an intentional managed-tag exception.
  • Build vs Publish Separation: build.yml writes artifacts to the remote CAS; publish.yml only exports artifacts already present in the CAS for that exact resolved SHA.
  • e2e Workflow Gate: e2e.yml runs only via workflow_dispatch against an already-published tag. It does not gate PRs.
  • Atomic Matrices: Do not cancel or serialize matrix siblings (default, nvidia, gaming, nvidia-gaming) without explicit human approval.
  • Truth in Reporting: Never report CI as green while workflows are pending, queued, or skipped.

Read the full file on GitHub · 74 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 · +10 lines 80b145e6e1f9
  2. 11d ago First seen · 64 lines · 29 tokens per session scan A c8817d321e46

Subscribe to this mod's changes

dakota-ci is a skill published in the GitHub repository projectbluefin/dakota (150 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 886 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.

Related

Other skills, from other repositories

import-prom-rule

Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…

ccfos/nightingale · 125 tokens

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

configure-env-variables

Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…

microsoft/power-platform-skills · 119 tokens

atmos-profiles

Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.

cloudposse/atmos · 35 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens