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 rana/skills --skill crystallizegit clone --depth 1 https://github.com/rana/skillsWrote 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/rana/skills/crystallize)<a href="https://agentmods.dev/skills/rana/skills/crystallize"><img src="https://agentmods.dev/badge/skills/rana/skills/crystallize.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 | $0.00030 | $0.00493 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
crystallize 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 7d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read all project markdown documents to ground in the project's actual state.
Crystallization Review
Apply the editorial knife across two dimensions: structural simplification and communication quality.
Structural Simplification
- Would you simplify anything? — What's more complex than it needs to be? What's solving a problem that doesn't exist yet?
- Would you remove anything? — What's dead weight? Vestigial decisions? Features that don't earn their keep? Could this be reconstructed from the code and domain knowledge alone — and if so, is it documentation weight masquerading as documentation value?
- Would you restructure anything? — What would be clearer reorganized? What's in the wrong document or section?
- What are you not enthusiastic about? — Where does the design feel forced, over-engineered, or uncertain? Be honest.
- What are you enthusiastic about? — What's working well? What's elegant? Reinforce the strengths.
- Is the design crystalline? — Does every element serve a purpose? Can you see through it clearly?
Communication Quality
- AI readability — Can a fresh Claude session navigate these documents efficiently? Are identifiers unambiguous? Is structure consistent enough for pattern-matching?
- Onboarding — Could a new developer (or a new Claude session) understand the project from docs alone? Where would they get lost?
- Staleness — Are there references to things that no longer exist? Outdated state descriptions? Dead links?
- Redundancy vs. value — Is the same information in multiple places? Is that useful (different audiences need different formats) or dead weight (documentation that exists only because someone wrote it)?
Focus area: $ARGUMENTS
For every proposal:
- What to change and why (the simplification or removal)
- What's preserved (nothing valuable is lost)
- Where the change belongs
Present as an action list. No changes to files — document only.
Output
Order proposals by complexity reduction impact. State the total count when complete.
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.
- 7d ago First seen · 47 lines · 30 tokens per session scan A 30d3a4bc094b
crystallize is a skill published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 493 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
skill-audit
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
second-pass-review
Independent audit of sanitized specs in workspace/output/. Three parallel LLM-based reviewer roles check structural leakage, content contamination, and behavioral completeness. Run AFTER Layer 5 sanitization, BEFORE implementation handoff.
check-pr
Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR…
codex-review
Get an independent code review from OpenAI Codex (GPT-5) on uncommitted changes, a branch diff, a PR, or a specific module — returns findings grouped by severity with file:line references. Use when the user says "review this", "review my changes", "check this PR", "what did I miss", or before they commit or merge…