Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jordiboehme/crystallinenpx agentmods add skills/jordiboehme/crystalline/crystalline-provisioningWrote 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/jordiboehme/crystalline/crystalline-provisioning)<a href="https://agentmods.dev/skills/jordiboehme/crystalline/crystalline-provisioning"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-provisioning/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/jordiboehme/crystalline/crystalline-provisioning"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-provisioning.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 | $0.00094 | $0.02572 |
| Opus 5.5 | $0.00038 | $0.01029 |
| Sonnet 5.5 | $0.00019 | $0.00514 |
| Haiku 4.5 | $0.00009 | $0.00257 |
Grade A, and why
crystalline-provisioning 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crystalline Provisioning
A domain can ship the tools its knowledge depends on - skills, commands, agents and MCP servers - into the person's coding harnesses. The person decides; you do the legwork and show each step first.
Before you start
Call list_domains and take the domain's path. Stop and say why when the domain is virtual or when that path does not exist on the machine your shell sees: the server then runs elsewhere, and the person provisions with crystalline provision on their own machine. Call provision with action: "status"; if it lists no harness, the person runs crystalline install <harness> first. Call origin_status: if the domain has a team origin, choose the location from "Team domains" below. If origin_status is not among your tools, or refuses because collaboration is off, the domain is local; do not turn collaboration on.
Choose where the tools live
For a local domain the tools live in a git repo beside the domain folder, by default <domain-folder>-tools, declared from the MANIFEST as ../<domain-folder>-tools/<kind>. If the person names an existing repo, propose git clone <url> <path>; for a new one, propose git init <path>. Show the exact path and command, then stop: end your turn and run it only after the person says yes.
Lay out the folders
Create one folder per kind, and only the kinds the person will use:
skills/<name>/SKILL.mdwith frontmatternameequal to the folder name and a one-linedescription. Scripts and references inside the skill folder ship with it.commands/<name>.mdorcommands/<namespace>/<name>.md, frontmatter optional (description,argument-hint).agents/<name>.mdwith frontmatternameanddescription; the body is the agent's instructions. Write agents in markdown, neverx.mdbesidex.toml.mcps/<name>.json, a JSON object withnameand aserverobject: stdio ascommand,argsandenv, HTTP as"type": "http",urlandheaders.
{ "name": "tide-tables", "server": { "command": "tide-mcp", "args": ["--stdio"] } }
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 Changed · +2 lines c1f5825fa8b9
- 13d ago First seen · 121 lines · 94 tokens per session scan A 793d44f9db5a
crystalline-provisioning is a skill published in the GitHub repository jordiboehme/crystalline (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 94 tokens to every session and 2,572 once invoked, about $0.0004 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 2026-10-03.
Other skills, from other repositories
define-jumbo-goals
Add Jumbo goals liberally to decompose objectives into finite units of work with bounded context. Use when defining new Jumbo goals from user requests, or to augment your own work to maintain scope while ensuring complementary work is registered.
jumbo-design-goal
Pre-definition collaborative discovery. Aligns a proposed goal with project audience, pains, and value propositions; surfaces design gaps and open questions before handing off to define-jumbo-goals.
refine-jumbo-goals
Use when Jumbo goals need refinement before implementation. Curates relations to project entities so the implementing agent receives optimal architectural context.
start-jumbo-goal
Use when starting a Jumbo goal. Loads goal context, scope, and architectural constraints, then guides the agent through disciplined execution within defined boundaries.
codify-jumbo-goal
Use when a Jumbo goal has been approved by QA review and needs architectural reconciliation before closing. Captures new learnings, updates stale entities, and ensures documentation reflects the work performed.
review-jumbo-goal
Use when a Jumbo goal needs QA review after implementation. Runs the review protocol, verifies every objective, criterion, and related entity constraint, and approves the goal for codification or rejects it with feedback.