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-capturegit 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-capture)<a href="https://agentmods.dev/skills/jordiboehme/crystalline/crystalline-capture"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-capture/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-capture"><img src="https://agentmods.dev/badge/skills/jordiboehme/crystalline/crystalline-capture.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 | $0.00047 | $0.08223 |
| Opus 5.5 | $0.00019 | $0.03289 |
| Sonnet 5.5 | $0.00009 | $0.01645 |
| Haiku 4.5 | $0.00005 | $0.00822 |
Grade A, and why
crystalline-capture 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 5d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crystalline Capture
Capturing what you learn while you work, as engrams, is the core of Crystalline. Treat it as a normal byproduct of the task, not a separate chore to remember at the end. A session-end reminder may ask you to review the conversation for uncaptured learnings - handle it with this skill and finish quietly when nothing qualifies. That reminder sometimes carries a maintenance ask alongside it, and when it names focus domains, pass exactly those to evolve_engrams instead of sweeping everything. It can also carry a sharing ask counting work a team domain has not sent to the team: that one belongs to crystalline-collaboration - propose share_changes for the domain it names, or ask which domain first when it counts several, and wait for a yes, because sharing publishes somebody's work for review. It can also name a domain's Reflection with open items: call reflect for that domain and work the queue, what people changed first. Present what you write with the crystalline-presentation skill (read it with the skills tool, name crystalline-presentation, if it is not installed): the PACT's ## Presentation first, an element only where it serves the reader.
Some deployments are read-only: if the server instructions or an injected prompt say this deployment's knowledge is read-only and curated externally, stand down on capture. The write tools are not exposed there and this whole skill does not apply; search and read instead.
A domain whose routing line says (read-only), or whose row carries read_only: true (a domain row's read_only), is not a place for you to write. It is locked, your role only reads it, or it is not on your account's write list. Search and read it, and write where the routing block allows.
What to capture
Capture durable knowledge: decisions, confirmed facts, repeatable patterns, gotchas, conventions, lessons learned the hard way, known risks and explicitly speculative ideas or proposals. Do not capture transient debugging steps, one-off scratch state, or knowledge so narrow it only ever matters to the current session.
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.
- 5d ago Changed 6e7d74b519fe
- 8d ago Changed 5f39bd139608
- 13d ago Changed 7a24145358c7
- 14d ago Changed · +2 lines 2c587a765c83
- 15d ago Changed · +4 lines 06fe1780bb14
- 16d ago Changed · +2 lines 4b00406415eb
- 17d ago Changed a2162ab6c7cc
- 25d ago Changed · +2 lines 06a497dfac6a
- 28d ago Changed · +3 lines e1b371a10c61
- 1mo ago First seen · 176 lines · 47 tokens per session scan A 5975c6c6e263
crystalline-capture is a skill published in the GitHub repository jordiboehme/crystalline (17 stars, last pushed 2d ago), licensed MPL-2.0. It adds 47 tokens to every session and 8,223 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
jumbo-add-guideline
Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
jumbo-add-invariant
Use liberally when you discover or are told a non-negotiable constraint — something that must always be true regardless of context. Registers the invariant so future sessions never violate it.
jumbo-context-maintenance
Use when implementation discovers durable project context that must be recorded in Jumbo. Captures decisions, components, dependencies, relations, guidelines, and invariants during the work.
jumbo-correction-capture
Use when the user corrects an approach, constraint, workflow, or style. Converts corrections into Jumbo guidelines or invariants so future sessions receive the constraint.
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.
atomicmemory-cli
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.