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 szw321127/repowise --skill pk-auto-crystallizegit clone --depth 1 https://github.com/szw321127/repowiseWrote 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/szw321127/repowise/pk-auto-crystallize)<a href="https://agentmods.dev/skills/szw321127/repowise/pk-auto-crystallize"><img src="https://agentmods.dev/badge/skills/szw321127/repowise/pk-auto-crystallize/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/szw321127/repowise/pk-auto-crystallize"><img src="https://agentmods.dev/badge/skills/szw321127/repowise/pk-auto-crystallize.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 | $0.00033 | $0.00558 |
| Opus 5 | $0.00016 | $0.00279 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
pk-auto-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 11d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PK Auto Crystallize
Treat this skill as the preferred task-end entrypoint when the user wants the project knowledge loop to update with minimal manual JSON authoring.
Required Behavior
- Determine the target project root from an explicit path; otherwise use the current working directory.
- Resolve
../../scripts/pk-auto-crystallize.mjsrelative to thisSKILL.mdfile. - The wrapper delegates to
auto-crystallize-session.mjs. - If
.project-knowledge/project-profile.mdis missing, returnmode: no-knowledgeand skip crystallization entirely; do not scan touched files, create sessions, or create.project-knowledge/. - Prefer passing a JSON input file after the project path when the task summary, touched files, or session id are known.
- If
adoptedNodeIdsis omitted, allow the script to infer adopted recommended options frompk-preflightmatches. - Prefer explicit
touchedFiles;allowGitStatusFallbackmust be true before dirty git status is used as low-confidence evidence. - Accept
taskIdortaskDirfor generic task/process context. Prefer.tasks/<taskId>ortasks/<taskId>; compatible external workflow layouts such as.trellis/tasks/<taskId>are fallback inputs only. Treat process files as process sources and task text, not durable source evidence unless the project evidence policy explicitly allows them. - If
incubatingNodesis omitted and no practice matches, allow the script to create an incubating practice plus candidate option fromtaskTextandtouchedFiles. - Report the result in Chinese and include
mode, inferred adopted nodes, generated incubating nodes, touched files, task/process sources when present, and the next suggested skillpk-lint; when skipped because knowledge is uninitialized, suggestpk-initinstead.
JSON Input Shape
{
"sessionId": "session-YYYY-MM-DD-topic",
"title": "本轮任务标题",
"topic": "本轮任务主题",
"taskText": "用于匹配已有实践的任务描述",
"taskId": "",
"taskDir": "",
"decisionSummary": "一句话总结本轮关键决策。",
"touchedFiles": [],
"allowGitStatusFallback": false,
"adoptedNodeIds": [],
"rejectedNodeIds": [],
"incubatingNodes": [],
"stableUpdates": []
}
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.
- 11d ago First seen · 45 lines · 33 tokens per session scan A 838be0efcb4d
pk-auto-crystallize is a skill published in the GitHub repository szw321127/repowise (21 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 558 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.