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 skills/kaevdm/duneboard/duneboard-init-projectnpx skills add KaEvDm/DuneBoard --skill duneboard-init-projectgit clone --depth 1 https://github.com/KaEvDm/DuneBoardWrote 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/kaevdm/duneboard/duneboard-init-project)<a href="https://agentmods.dev/skills/kaevdm/duneboard/duneboard-init-project"><img src="https://agentmods.dev/badge/skills/kaevdm/duneboard/duneboard-init-project.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 | $0.00058 | $0.01168 |
| Opus 5 | $0.00029 | $0.00584 |
| Sonnet 5 | $0.00012 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
duneboard-init-project 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 6d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DuneBoard Project Init
Bootstrap a local repository so agents and humans can use DuneBoard there.
Use this before organizing or importing real work into a new target project.
Inputs
Identify:
- target project root
- DuneBoard workspace root
- project display name
- project id for
.duneboard/projects.local.json - whether the target already has
AGENTS.md,CLAUDE.md, or other agent instruction files
Use a stable lowercase project id with hyphens, for example that-one-book.
Create Board Skeleton
Create the project-local board config:
.duneboard/config.yml
tasks/
Use this config shape:
name: Project Name
version: 0.1
task_roots:
- tasks
id_prefix: DB
default_status: draft
workflow:
statuses:
- draft
- ready
- in_progress
- blocked
- review
- done
- canceled
done_statuses:
- done
active_statuses:
- ready
- in_progress
- blocked
- review
Do not delete or move existing planning files.
Install Agent Guidance
Make the target repository self-describing for future agents:
.codex/skills/duneboard-agent/SKILL.md
.codex/skills/duneboard-agent/agents/openai.yaml
.claude/skills/duneboard-agent/SKILL.md
AGENTS.md
Do not put the installed project-local skill in a plain root-level skills/
directory. That is useful as a source package inside DuneBoard itself, but it is
not where Codex or Claude Code discover project skills.
The local skill must include exact commands for the target root. If the target project does not own the DuneBoard CLI, prefer the stable wrapper from the DuneBoard workspace:
C:\path\to\DuneBoard\scripts\DuneBoard.ps1 --root C:\path\to\project preflight --compact
Use pnpm --dir C:\path\to\DuneBoard dune --root C:\path\to\project ... only
as a fallback when the wrapper is unavailable.
Minimal local skill body:
---
name: duneboard-agent
description: Work with this repository's DuneBoard board in tasks/. Use when planning, claiming, updating, blocking, releasing, or closing tasks.
---
# DuneBoard Agent Skill
- `tasks/` Markdown files are the source of truth.
- Do not invent task IDs; create tasks through the DuneBoard CLI.
- Do not delete or move source project files when updating the board.
- Use dependencies only for real sequencing constraints.
Validate and inspect work:
```powershell
C:\path\to\DuneBoard\scripts\DuneBoard.ps1 --root C:\path\to\project preflight --compact
```
For a narrow user-requested fix that touches only one or two files and does not
touch DuneBoard task files or an active board task, skip claim/note/release and
run only the relevant validation. Return to the full workflow if the work grows.
What ships with it
1 file 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.
- 6d ago First seen · 180 lines · 58 tokens per session scan A ca00a977cd1c
duneboard-init-project is a skill published in the GitHub repository KaEvDm/DuneBoard (11 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,168 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
ship-and-babysit
End-to-end PR shipping workflow for tinyhumansai/openhuman: commit local changes, push to the user's fork, open or reuse a PR against main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user asks to ship, open a PR, monitor CI, address review comments, or 'babysit' a branch.
fo-dispatch-recovery
Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual Agent() template) and Context Budget Failure/Dead Ensign Handling (the budget-unavailable stderr conditions, the recovery clause, dead-ensign bookkeeping). Read ONLY at its resident triggers inside claude-fo-dispatch.md — a non-zero or…
fo-status-viewer
First-officer status query/mutate/display surface — the status command flag docs, --set field docs, canonical captain-facing invocations, the Captain-Facing State Display rendering, and the GitHub-issue-filing approval gate. Invoke at the first ad-hoc status question, --set mutation, --next-id/--resolve lookup, or…
present-gate
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.
ai-seo
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…