crystallize

A workflow for turning the current session into a reusable coding-agent skill, usually by placing it in a queue for human approval. It can also create a live skill when that is explicitly requested.

In plain words
What is it for?
Use it after developing a procedure that should recur, to save that procedure as a candidate skill or, explicitly, an active skill.
Why use it?
It preserves a repeatable way of working so it can be reused in later sessions instead of reconstructed from memory.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kirodotdev/kirocrew/crystallize
Any agent
npx skills add kirodotdev/KiroCrew --skill crystallize
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,009 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.02009
Opus 5 $0.00017 $0.01005
Sonnet 5 $0.00007 $0.00402
Haiku 4.5 $0.00003 $0.00201

Measured 3d ago against content hash a8e677133437, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

src/kiro_crew/builtin_skills/crystallize/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crystallize a session into a skill

Use this whenever the user asks to capture work as a reusable skill — "crystallize this", "create a skill", "save this as a skill", "make this reusable", or "turn this into a skill". This is the on-demand counterpart to the automatic post-session skill generation: the user is telling you now that the work is worth keeping.

Two modes, chosen from the user's wording:

  • Candidate (default). Stage the skill in the pending queue for human approval. Every phrasing above means this unless the user says otherwise.
  • Live (explicit only). Write the skill straight to a live, immediately-loadable location, bypassing approval. Take this path ONLY when the user explicitly says "create a live skill" or "create an active skill" (or confirms it when asked). Never infer it from a plain "create a skill" — that stays a candidate.

When to use

  • The user says any trigger phrase above (candidate mode), or explicitly asks for a "live" / "active" skill (live mode).
  • The session demonstrated a procedure that will recur — one a future session, working on a DIFFERENT target, would run again substantially unchanged: a repeatable debugging method for a class of error, a fixed command/API sequence, a verification technique, a research-synthesis flow.

Apply the same recurrence test the automatic pass uses: name the future session that would load this skill and the different target it would run against. If the only honest answer reuses this session's own artifact — this bug, this file, this component, this one question — the procedure does not recur. Effort is not evidence of recurrence: a long, many-step, genuinely difficult session is still one-off if its steps were chosen for one target.

Do not crystallize a task done once and now finished (a specific bug's fix, a one-time audit or trace of one component, a migration, a probe run to answer a question that is now answered), a design or planning discussion, a narrative of what happened in this session, a trivial one-shot answer, a one-off failure, or a session that touched credentials / sensitive paths. Being asked does not make a one-off reusable — but the call is the user's, not yours. When the session carries no recurring procedure, say so and name what makes it one-off, then let them decide; if they still want it captured, crystallize it. Never silently decline a direct request.

Read the full file on GitHub · 167 lines

Changes

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.

  1. 3d ago First seen · 167 lines · 35 tokens per session scan A a8e677133437

Subscribe to this mod's changes

crystallize is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 2,009 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 2026-08-30.

Related

Other skills, from other repositories

reskin

Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…

CopilotKit/CopilotKit · 154 tokens

copilotkit-setup

Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.

CopilotKit/CopilotKit · 56 tokens

copilotkit-integrations

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

CopilotKit/CopilotKit · 61 tokens

a2ui-renderer

Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…

CopilotKit/CopilotKit · 175 tokens

copilotkit-develop

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

CopilotKit/CopilotKit · 46 tokens

copilotkit-upgrade

Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.

CopilotKit/CopilotKit · 48 tokens