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-debug-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-debug-recall)<a href="https://agentmods.dev/skills/zengliangyi/chatcrystal/chatcrystal-debug-recall"><img src="https://agentmods.dev/badge/skills/zengliangyi/chatcrystal/chatcrystal-debug-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-debug-recall"><img src="https://agentmods.dev/badge/skills/zengliangyi/chatcrystal/chatcrystal-debug-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00054 | $0.00611 |
| Opus 5 | $0.00027 | $0.00305 |
| Sonnet 5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
chatcrystal-debug-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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatCrystal Debug Recall
Use this skill when the task is clearly about diagnosis or debugging. Keep the skill thin and let ChatCrystal Core handle retrieval.
Workflow
- Trigger when the task includes failing tests, compiler errors, runtime exceptions, broken dependencies, environment problems, or performance regressions.
- If
recall_for_taskis available, call it before proposing a fix with:mode: "debug"task.goal: the concrete debugging objectivetask.task_kind: "debug"task.project_dirandtask.cwdwhen knowntask.branchwhen knowntask.related_filesortask.files_touchedwhen knowntask.error_signaturespopulated with the most useful identifiers available
- Prefer concrete signals such as:
- failing test names
- exception classes
- error codes
- log signatures
- package or tool versions when they materially affect the failure
- Prioritize returned memories that explain root cause, remediation, or known pitfalls.
- Use recalled memories to sharpen diagnosis, not to skip verification in the current environment.
Example MCP Input
Use this shape when calling recall_for_task for debugging:
{
"mode": "debug",
"task": {
"goal": "Diagnose failing build after TypeScript upgrade",
"task_kind": "debug",
"project_dir": "/path/to/project",
"cwd": "/path/to/project",
"branch": "upgrade/typescript",
"related_files": [
"server/src/cli/mcp/server.ts",
"tsconfig.base.json"
],
"error_signatures": [
"TS2322",
"Type is not assignable"
],
"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.
- Keep
project_memoriesprimary andglobal_memoriessecondary. - If the response includes warnings or
no-matches, continue debugging normally. - Do not overfit to a recalled fix when the current failure signature diverges materially.
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.
- 9d ago First seen · 77 lines · 54 tokens per session scan A 97ce5f0d33b3
chatcrystal-debug-recall is a skill published in the GitHub repository ZengLiangYi/ChatCrystal (58 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 611 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
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
skillnote-doctor
A diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
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.
raytsystem-lint
Run deterministic integrity, provenance, projection, link, alias, operation, and secret checks over raytsystem. Use for LINT, health checks, pre-commit verification, stale projection diagnosis, broken evidence, or semantic review; never auto-fix canonical knowledge.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
megalinter-setup
Install or upgrade MegaLinter on a repository. Use when the user wants to add MegaLinter to a project, set up linting CI, update MegaLinter configuration or version, or says "install megalinter", "setup linting", "add code quality checks". Always goes through npx mega-linter-runner (--install or --upgrade), then…