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 skills add datacore-one/datacore --skill decision-boardgit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/datacore-one/datacore/decision-board)<a href="https://agentmods.dev/skills/datacore-one/datacore/decision-board"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/decision-board/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.
<a href="https://agentmods.dev/skills/datacore-one/datacore/decision-board"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/decision-board.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00160 | $0.01643 |
| Opus 5.5 | $0.00064 | $0.00657 |
| Sonnet 5.5 | $0.00032 | $0.00329 |
| Haiku 4.5 | $0.00016 | $0.00164 |
Grade A, and why
decision-board 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 17d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision board
The owner makes decisions on a page, not in chat. This skill covers only presentation and behaviour. Content is whatever the session is working through, and the owner steers it.
Stays local
- Write the page to
$DATACORE_STATE/decision-boards/<YYYY-MM-DD>-<slug>.html(default~/.datacore/state/decision-boards/). Saved answers are filed into itsanswers/subfolder (see "Reading choices back"). The directory must be owner-only (0700), and artifacts are published atomically as 0600. This state is outside synchronized source repositories. - Open the page with
open <path>. - Never publish it to claude.ai (Artifacts), a gist or any hosted URL, even privately. If a hosted page seems necessary, ask first.
- Inline all CSS and JS. Use local/system font fallbacks without external font requests. The generated page has a restrictive content policy. Reference links accept only explicit HTTP(S) URLs; executable or other URL schemes are rendered as text.
Look: PLUR brand
- Fonts. Outfit for everything (weight 200 for the title, 300 for body text, 400 for labels). JetBrains Mono for ids, counts and meta lines.
- Light mode. Background
#fafaf9, surface#ffffff, text#1a1a1a. - Dark mode. Background
#0e0f14, surface#15171d, text#f0f0f2. Switch withprefers-color-scheme. - Accents.
#22d3ee,#f0a050,#a78bfaand#34d399, used only to show sequence.#e8695fis the only status colour. The primary button is#7c3aed. - Separators. Hairline rules between rows, not boxed cards. Uppercase labels get a little letter-spacing.
Layout
- Masthead: a small uppercase eyebrow, a light-weight title, a one-sentence lede and an "as of" line. Beside it, a four-step path showing where this review stands.
- Sticky bar:
- "N of M decided";
- a "Use the suggestions for the rest" link;
- the save status;
- a Save button.
- Groups. Items sit under section headings, each with a count.
- Rows. Each row has, in order:
- a short id (A1, A2…) and any links, on a mono meta line;
- a one-line title that states the decision;
- one or two sentences of context;
- an optional preview block;
- the options as stacked choices, each with a one-line consequence, with the suggested one tagged "suggested";
- a "Note for Claude" field.
- Noted list. Anything that needs no decision goes in a "Noted, nothing to decide" list at the end of its section, not as a question.
- Phone width. At about 400px wide, everything stacks into one column.
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.
- 17d ago Changed · +7 lines 2da4cb9ddd6a
- 1mo ago Changed · +2 lines 4577877cee56
- 1mo ago First seen · 91 lines · 160 tokens per session scan A 35076e6020c7
decision-board is a skill published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 160 tokens to every session and 1,643 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
learn-from-correction
Propose a principle edit to a skill or persona file based on a (agentoutput, humanoutput) correction pair. Outputs a proposal markdown for human review - never auto-edits the target file.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
quiz-me
Use right after writing or editing code or files for the user — before ending your turn — to quiz them on what was just built and confirm they actually understand it. Also triggers on "quiz me", "test my understanding", "check what I learned", "comprehension check", or recovering the understanding that vaporizes when…
add-editor
Wire Deus's memory + evolution layers into an external code editor (Zed and other ACP/MCP clients) so the editor's own agent gains Deus's vault recall and self-improving reflexion loop. Configuration only — no new code. Triggers on "add editor", "use Deus in my editor", "zed integration", "editor integration", "wire…
add-llama-cpp
Install and verify a local llama.cpp server for optional Deus local-generation experiments. Keeps Ollama as the required default for embeddings and judge work.
code-review
Multi-agent code review with learning feedback loop — reviews PRs using parallel specialized agents (style, logic, security) with confidence scoring and false-positive reduction.