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 jordiboehme/crystalline --skill crystalline-presentationgit clone --depth 1 https://github.com/jordiboehme/crystallineWrote 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-presentation)<a href="https://agentmods.dev/skills/jordiboehme/crystalline/crystalline-presentation"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-presentation/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-presentation"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-presentation.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 | $0.02732 |
| Opus 5.5 | $0.00038 | $0.01093 |
| Sonnet 5.5 | $0.00019 | $0.00546 |
| Haiku 4.5 | $0.00009 | $0.00273 |
Grade A, and why
crystalline-presentation 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 8d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crystalline Presentation
A reflection is read by people. Present it the way a good technical writer would: clear prose first, and a diagram, callout, table or status label where the content calls for one. Engrams are read by agents and people, so the same elements may help there when they make knowledge easier to store, describe or find.
When it applies
- You write or update a reflection, or
PACT.md. - You work a
reflectqueue: feedback items, update items and review items. - You write or edit an engram where a table or a diagram would make it easier to find or to use.
The PACT first
Before you write a page, read the domain's PACT.md with read_reflection. Its ## Presentation section says which diagrams, callouts and tables help these readers and what to avoid. It narrows or extends the defaults in this skill, and where the two differ, the PACT wins. A PACT that says "no diagrams" means no diagrams, even where this skill requires one, and a PACT that asks for plain text and tables only means no callouts and no diagrams, not even a caution before an irreversible step: say the warning in a sentence.
When the PACT has no ## Presentation section, use the defaults below. If you see a pattern the readers would want written down, propose it: write it into PACT.md when you may curate, otherwise open a thread with discuss.
When you rewrite a whole page, pass the checksum from read_reflection as expected_checksum, so a change a person made since your read is refused instead of overwritten.
Record the engrams each section was built from with sources on write_reflection, as permalinks in this domain or crystalline://<domain>/<permalink> addresses for another domain; never write them into the page as HTML comments or text.
Where an element is required
These shapes need their element. A numbered list or a paragraph is not enough for them.
- Messages or steps between two or more parties in a fixed order (a client, a server, a third service): a
sequenceDiagram. Always, even for three steps. - A process with a decision or a branch ("if the check fails, ..."): a
flowchart. - States and the moves between them (draft, active, closed): a
stateDiagram-v2. - Three or more options compared on the same attributes: a table, one row per option. Not a bullet list, and not one
##section per option. When the source gives a verdict, add a verdict column with status labels. - An action that cannot be undone, or a risky one: a
> [!WARNING]or> [!CAUTION]callout inside the section that describes that action, directly before or after the step. Never in the page lead (the text above the first##), and never folded.
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.
- 8d ago First seen · 161 lines · 94 tokens per session scan A 63105dec591b
crystalline-presentation is a skill published in the GitHub repository jordiboehme/crystalline (17 stars, last pushed 2d ago), licensed MPL-2.0. It adds 94 tokens to every session and 2,732 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 2026-10-20.
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.
refine-jumbo-goals
Use when Jumbo goals need refinement before implementation. Curates relations to project entities so the implementing agent receives optimal architectural context.
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.
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.
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.
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.