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 ZengLiangYi/ChatCrystal --skill chatcrystal-task-recallgit clone --depth 1 https://github.com/ZengLiangYi/ChatCrystalWrote 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/zengliangyi/chatcrystal/chatcrystal-task-recall)<a href="https://agentmods.dev/skills/zengliangyi/chatcrystal/chatcrystal-task-recall"><img src="https://agentmods.dev/badge/skills/zengliangyi/chatcrystal/chatcrystal-task-recall/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/zengliangyi/chatcrystal/chatcrystal-task-recall"><img src="https://agentmods.dev/badge/skills/zengliangyi/chatcrystal/chatcrystal-task-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.00606 |
| Opus 5 | $0.00033 | $0.00303 |
| Sonnet 5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
chatcrystal-task-recall 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatCrystal Task Recall
Use this skill as a thin workflow on top of ChatCrystal Core. Do not invent a parallel memory system in the skill.
Workflow
- Decide whether the task is substantial enough to justify recall.
- Trigger for non-trivial
implement,refactor,migration,config,investigate, oroptimizationwork. - Skip trivial edits, one-line answers, or purely conversational requests.
- If
recall_for_taskis available, call it before substantive work with:mode: "task"task.goal: the concrete task objectivetask.task_kind: the best matching task kindtask.project_dirandtask.cwdwhen repository context existstask.branchwhen knowntask.related_filesortask.files_touchedwhen knowntask.source_agentwhen the runtime has a stable value
- Treat
project_memoriesas primary context andglobal_memoriesas supplemental context. - Apply recalled pitfalls, patterns, and prior decisions before proposing or writing code.
Example MCP Input
Use this shape when calling recall_for_task for implementation or investigation work:
{
"mode": "task",
"task": {
"goal": "Add a paginated notes export endpoint",
"task_kind": "implement",
"project_dir": "/path/to/project",
"cwd": "/path/to/project",
"branch": "feature/export-notes",
"related_files": [
"server/src/routes/notes.ts",
"shared/types/index.ts"
],
"source_agent": "codex"
},
"options": {
"project_limit": 5,
"global_limit": 3,
"include_relations": true
}
}
Full Mode
Full mode requires ChatCrystal Core plus MCP access to recall_for_task.
- Prefer the current repository or workspace path so Core can derive
project_key. - Surface relevant warnings such as
no-project-keyorno-matches, but do not treat them as failures. - If recall returns nothing useful, continue the task normally.
Degraded Mode
If ChatCrystal Core or the MCP tool is unavailable:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 69 lines · 66 tokens per session scan A c7d7df0c8ad8
chatcrystal-task-recall is a skill published in the GitHub repository ZengLiangYi/ChatCrystal (58 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 606 once invoked, about $0.0003 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
raytsystem-save
Stage a cited synthesis as a typed raytsystem DRAFT bundle and escaped preview. Use for SAVE, preserving a verified query answer, preparing a knowledge proposal, or creating a reviewable draft; never treat SAVE as canonical promotion or publication.
workspace-knowledge-sync
Syncs knowledge to the agentic-harness knowledge base and AGENTS.md learned facts. Use when the assistant discovers new patterns, learns user preferences, workspace facts, or identifies information worth preserving for future sessions. Integrates with platform-engineer (formerly tech-assistant) for automatic trigger…
workspace
Scaffold and manage the stateless AI workspace — context, packs, repos, and knowledge for multi-repo orchestration.
mistakes
List past mistakes engram has learned in this project — failures, regressions, broken assumptions. Use before starting a non-trivial change to surface relevant prior failures, or when debugging to check if this issue has been seen before.
query
Query engram's local knowledge graph for structural context — function calls, imports, type relationships, mistake history, ADRs. Use when the user asks "how does X work in this project", "what calls Y", "where is Z used", or any structural question that doesn't need file content.
audit-history
Use when reviewing past agent sessions, auditing memory health, identifying repeated corrections or friction, cleaning up stale memories, proposing new skills and rules from usage patterns, or identifying mechanical improvements (testing, linting, static analysis, tooling) that could improve outcomes.