lov-auto-context SKILL.md skillA
lov-auto-context from lovstudio/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lovstudio/skills/lov-auto-context@v0.4.2Pins v0.4.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lovstudio/skills
- Path
skills/auto-context/SKILL.md- Versions recorded
- 6
- Latest version
- v0.4.2, committed Sep 25, 2026
- First version recorded
- Aug 10, 2026
- Size
- 9,434 bytes
- Repository stars
- 72
- License
- MIT
Manual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, topic drift, stale noise), AND takes concrete context-shaping actions: writing project memory, updating global or project CLAUDE.md (with diff + confirm), and recommending harness commands like /fork, /compact, /btw. Covers the full surface of context-affecting operations Claude can reach — direct file edits are auto-executed or confirmed based on sensitivity; harness-only commands…
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
# 上下文哨兵 · Context Sentinel Not just a health check — a full operator over everything that shapes context. Three layers by action sensitivity: | Layer | Examples | Behavior | |-------|----------|----------| | **Auto-execute** | write project memory, update `MEMORY.md` index | Do it, report path | | **Confirm-first** | edit global agent instructions, edit project `CLAUDE.md`, overwrite/delete existing memory | Show diff, wait for "yes" | | **Suggest-only** | `/fork`, `/compact`, `/btw`, new session | Print the exact command to paste | The harness owns `/fork` and `/compact`; this skill cannot invoke them. But it can do everything else and will. ## Auto Mode (via Plugin Hook) When the skill-publisher plugin is enabled, a `UserPromptSubmit` hook monitors transcript size. Above threshold (40+ entries or 150KB+), it injects a lightweight `<auto-context>` reminder. **When you see `<auto-context>`:** | Context State | Action | |---------------|--------| | Mostly relevant | Continue, say nothing | | Some stale noise | Mentally deprioritize, proceed | | Mostly irrelevant | Suggest `/fork` or `/btw` with exact command | …
Read the whole file at its exact version.
How to install
mdr add lovstudio/skills/lov-auto-context@sha256:aa135dda2d1f540fThe line at the top of this page pins the label v0.4.2, 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_ie3kyqijxe2pdtdr)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Aug 10, 2026 and Sep 25, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.4.2 latest | 2026-09-25 | 4b67fd1 | 9,434 B | A | view · diff |
| v0.4.0 | 2026-09-07 | a09848e | 8,138 B | A | view · diff |
| v0.4.0 | 2026-08-23 | 00fafa8 | 8,132 B | A | view · diff |
| v0.3.1 | 2026-08-10 | d704a55 | 7,410 B | A | view · diff |
| v0.3.1 | 2026-08-10 | 22e49cf | 6,783 B | A | view · diff |
| v0.3.1 | 2026-08-10 | 08d33b8 | 6,783 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 (9434 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
lovstudio/skills · 72 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ie3kyqijxe2pdtdr GET https://markdownregistry.com/api/v1/resolve?ref=lovstudio/skills/lov-auto-context GET https://markdownregistry.com/api/v1/blob/aa135dda2d1f540f163e670fa742ea75598af04312974889b33d7645ac178664
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.