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 agentmods add instructions/projectbluefin/dakota/agents-mdgit clone --depth 1 https://github.com/projectbluefin/dakotaWrote 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/instructions/projectbluefin/dakota/agents-md)<a href="https://agentmods.dev/instructions/projectbluefin/dakota/agents-md"><img src="https://agentmods.dev/badge/instructions/projectbluefin/dakota/agents-md.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 | $0.00852 | $0.00852 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
dakota AGENTS.md 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dakota agent guide
Dakota is Project Bluefin's bootc OCI desktop image, assembled from source with
BuildStream 2. This is not the RPM-based Bluefin build: do not use dnf,
rpm-ostree, COPRs, Containerfile package overlays, or post-build package
installation. Make image changes through BST elements.
Project skills live in .agents/skills/ and are discovered by Pi and GitHub
Copilot. Load only the skill matching the task; do not read every skill.
Non-negotiable safety
- Never write to any
ublue-os/*repository. No issues, comments, PRs, forks, dispatches, webhooks, or automated reports. Ask the human to report upstream manually. - Do not post GitHub comments, reviews, or edit PR bodies unless explicitly asked. When asked, post at most one combined comment and do not restate UI status.
- Never expose secrets or weaken signing, provenance, or supply-chain checks.
- Never push directly to
mainortesting. Work on a feature branch and leave final approval and merge to a human.
Sources of truth
- Read the file being changed and its callers before editing it.
- Use the relevant
.agents/skills/package for task-specific guidance. - Treat workflows, elements, the Justfile, and tests as current truth; prose that disagrees with executable configuration is stale.
- Verify external syntax and behavior in current official documentation before changing BuildStream, bootc, GitHub Actions, cosign, or skopeo usage.
- Preserve useful knowledge by correcting existing guidance. Do not append dated session notes, changelogs, or mandatory “lessons learned” entries.
Development workflow
- Branch from
upstream/testingunless the task explicitly targetsnext. - Push PR branches to
upstream, never a personal fork. - Run
just --listbefore inventing maintenance commands. Add a Justfile recipe when a repeatable repository operation has no existing entry. - Run
just validatefor BST or image changes. Use the narrowest additional check that exercises the change; CI performs full image verification. - Before claiming completion, inspect the diff and report the checks actually run. Do not claim CI is green while runs are pending or failing.
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.
- 4d ago First seen · 80 lines · 852 tokens per session scan A ed6bc5a8dd49
dakota AGENTS.md is an instructions file published in the GitHub repository projectbluefin/dakota (148 stars, last pushed today), licensed MIT. It adds 852 tokens to every session, about $0.0043 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.