daemon-forensics SKILL.md skillA
daemon-forensics from lingtai-ai/lingtai-kernel is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lingtai-ai/lingtai-kernel/daemon-forensics@v1.4.0Pins v1.4.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lingtai-ai/lingtai-kernel
- Path
src/lingtai/tools/daemon/manual/reference/forensics/SKILL.md- Versions recorded
- 6
- Latest version
- v1.4.0, committed Sep 9, 2026
- First version recorded
- Jul 11, 2026
- Size
- 5,076 bytes
- Repository stars
- 11
- License
- Apache-2.0
Nested daemon-manual reference for durable run artifacts, state/result inspection, transcripts, token ledgers, and interpreting exit 143/SIGTERM.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Daemon Forensics Reference
Read this when a run needs evidence beyond the notification or `check` result.
The run directory is durable evidence, not a disposable workspace.
## Durable run layout
New tasks get `daemons/em-<id>/` under the parent working directory (or the
standalone state root). Returned id, `daemon.json.run_id`, and folder name
identify the same new run; legacy ids can be ambiguous, so prefer exact run ids.
`reclaim` cancels all running manager-owned work but leaves its files. A molt clears conversation
context; it does not wipe durable stores or run folders.
```text
daemons/em-<id>/
├── daemon.json # identity, state, call parameters, previews
├── artifacts.json # metadata-only manifest, written at terminal time
├── result.txt # full result or bounded error text
├── .prompt # constructed system prompt
├── history/chat_history.jsonl
└── logs/{events,token_ledger}.jsonl
```
`artifacts.json` contains run-relative `{path, size, mtime, role}` entries plus
`state`, `result_path`, `error_path`, `artifacts_total`, and `truncated`. It
contains paths and metadata, never file contents. `check` prefers this
…Read the whole file at its exact version.
How to install
mdr add lingtai-ai/lingtai-kernel/daemon-forensics@sha256:72b59dd930416fbeThe line at the top of this page pins the label v1.4.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ui2hu2ueuldugx2s)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 11, 2026 and Sep 9, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.4.0 latest | 2026-09-09 | 336ec0e | 5,076 B | A | view · diff |
| v1.3.0 | 2026-07-28 | 80bc98c | 10,771 B | A | view · diff |
| v1.2.1 | 2026-07-19 | 88e075a | 10,691 B | A | view · diff |
| v1.2.1 | 2026-07-16 | d9dd484 | 10,979 B | A | view · diff |
| v1.2.1 | 2026-07-14 | b410ffc | 10,978 B | A | view · diff |
| v1.2.1 | 2026-07-11 | 57d1ea0 | 10,732 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5076 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
lingtai-ai/lingtai-kernel · 11 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ui2hu2ueuldugx2s GET https://markdownregistry.com/api/v1/resolve?ref=lingtai-ai/lingtai-kernel/daemon-forensics GET https://markdownregistry.com/api/v1/blob/72b59dd930416fbe4b4e2d1b649fd55627fe7393e67926a1f344a9f83a73a8d5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.