dakota: Skill for Claude Code

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

dakota-release is a skill for Claude Code, Codex from projectbluefin/dakota. It costs 21 tokens per session (924 once invoked), scanned A, original, MIT.

A release guide for promoting tested Dakota images, signing them, locking them to exact digests, and rolling back stable releases. A digest is an exact, immutable identifier for an image.

In plain words
What is it for?
Use it when changing release workflows, promoting an image to stable, verifying signatures, copying image digests, or rolling back a release.
Why use it?
It helps prevent an image from changing after it was verified and keeps signing, permissions, promotion, and rollback steps behind the required approval and evidence checks.

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-release/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-release

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-release"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 924 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Privilege Escalation · line 38
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 $0.00021 $0.00924
Opus 5 $0.00010 $0.00462
Sonnet 5 $0.00004 $0.00185
Haiku 4.5 $0.00002 $0.00092

Measured today against content hash a2176e425755, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dakota-release 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 today.

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-release/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dakota Release and Promotion

Release workflows cross a cryptographic and security boundary. Stop for human approval before changing signing identities, token permissions, provenance, or promotion gates.

When to Use

  • Modifying .github/workflows/execute-release.yml or rollback-stable.yml
  • Auditing or updating cosign keyless OIDC signatures or SLSA build provenance attestations
  • Managing image digest pinning, release receipts, or immutable tag promotion
  • Managing the Mon/Wed/Fri stable promotion schedule or rollback procedures

When NOT to Use

  • Routine CI build or validation workflow updates → load dakota-ci
  • Local container image builds or testing → load dakota-image
  • PR review workflows → load dakota-review

Core Process

  1. Trace Digest Flow: Map the exact SHA/digest path from build receipt to the target publication tag.
  2. Verify Cryptographic Policy: Confirm cosign certificate identity and issuer rules match repository policy.
  3. Lock Tested SHA: Always pin and verify the tested source commit SHA; fail closed if upstream advanced during testing.
  4. Verify Variant Coverage: Inspect the actual promotion and rollback workflows independently. rollback-stable.yml currently rolls back only dakota and dakota-nvidia, plus optional default-image multiarch tags. It does not roll back gaming or nvidia-gaming; recovery of those variants needs a separately reviewed plan, not an assumption of four-variant parity.
  5. Human Gate: Stop and obtain human confirmation before executing any production promotion, signing change, or tag rollback.

Invariants

  • Bookmark Invariant: main is a stable-release bookmark, not a branch for contributor PRs.
  • Rolling Streams: next and btw are rolling development streams; they never promote to :stable.
  • Promotion Gates: Stable promotion intentionally avoids the testsuite e2e gate. It enforces freshness locking, cosign verification, and digest-based copy.
  • Cryptographic Anchoring: Anchor --certificate-identity-regexp with ^...$ and restrict it strictly to the authorized publishing workflow and branch.
  • Digest-Based Promotion: Promotion operates on immutable digests (@sha256:...) or tested source SHAs, never by re-resolving a mutable tag name.

Read the full file on GitHub · 73 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. today Changed a2176e425755
  2. yesterday Changed · +24 lines scan B → A dfef94886df8
  3. 10d ago First seen · 49 lines · 21 tokens per session scan B 1f70f95e6c08

Subscribe to this mod's changes

dakota-release is a skill published in the GitHub repository projectbluefin/dakota (150 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 924 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.