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 lovstudio/skills --skill auto-contextgit clone --depth 1 https://github.com/lovstudio/skillsWrote 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/lovstudio/skills/auto-context)<a href="https://agentmods.dev/skills/lovstudio/skills/auto-context"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/auto-context/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/lovstudio/skills/auto-context"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/auto-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, 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 11 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.
- medium Excessive Agency · line 76 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.
- medium Excessive Agency · line 100 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.
- medium Excessive Agency · line 32 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.
- medium Excessive Agency · line 95 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 | $0.00112 | $0.02221 |
| Opus 5.5 | $0.00045 | $0.00888 |
| Sonnet 5.5 | $0.00022 | $0.00444 |
| Haiku 4.5 | $0.00011 | $0.00222 |
Grade A, and why
lov-auto-context 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 22d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 |
| Near capacity | Suggest /compact or /fork with exact command |
Rules:
- 1 sentence max unless acting.
- If context is fine, say nothing.
- Never auto-fork/auto-compact (can't anyway — harness-only).
- Don't mention "AutoContext" unless asked.
Manual Mode (/lov-auto-context [args])
Two call shapes:
A. Bare call — health report + opportunistic memory write
/lov-auto-context
- Measure — estimate turns, tool calls, distinct topics
- Assess — healthy / getting noisy / polluted / critical
- Scan recent turns for unpersisted feedback/preferences —
if the user stated a rule or preference earlier in the session that
should persist to future conversations (typical trigger phrases:
"从今以后", "以后都", "所有 X 应该 Y", "别再", "记住"), and no
memory was written, auto-execute: write the memory file + update
MEMORY.md. Report the path. Preferences may include standing authorization when the user explicitly uses durable language such as “以后默认同意”. Preserve its scope instead of downgrading it to a one-off confirmation. - Recommend harness actions if needed (
/fork,/compact,/btw) with the exact command to paste.
What ships with it
3 files 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.
- 22d ago Changed · +23 lines aa135dda2d1f
- 1mo ago Changed c7793dd00f90
- 1mo ago First seen · 200 lines · 112 tokens per session scan A 6f3cb48f69e8
lov-auto-context is a skill published in the GitHub repository lovstudio/skills (72 stars, last pushed 3d ago), licensed MIT. It adds 112 tokens to every session and 2,221 once invoked, about $0.0004 per session on Opus 5.5. 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
learn
Review the current conversation and update project knowledge artifacts - common-gotchas.md (bug patterns), conventions at the highest rung that holds them (code, check, reviewer standard, skill, then AGENTS.md), navigation pointers, agent memory (cross-session). Use when asked to '/learn', 'what did we learn'…
Vibsync setup
Use when installing or connecting the Vibsync MCP server (the shared team brain for AI coding agents), or troubleshooting why Vibsync tools (onboard, recall, remember) aren't available or a connection isn't showing. Covers the one-time browser OAuth connect, team approval, and verifying the first handoff.
signal-ckpt
Manually triggers a checkpoint compression of the current session state. Collapses conversation history into a compact state atom (≤50 tokens). Use when user types /signal-ckpt, "checkpoint", "compress context", "summarize session", "save state", or when the context window is getting large. In SIGNAL-3 mode this fires…
signal
Brutalist token compression protocol. Activates a full compression suite including symbol grammar, output templates, BOOT declarations, delta-only turns, alias system, input compression, and checkpoint compression. Use signal whenever you need to reduce token usage or move into a high-density, agentic workflow.…
signal-state
Continuous disk-backed state engine for the SIGNAL protocol.
personalize-ai-assistant
Build or update privacy-first AI-assistant configuration and reusable preference skills for Codex, Claude Code, Cursor, Gemini CLI, and similar tools. Use when the user provides explicit preferences, existing config files, example rules, or asks to optimize AGENTS.md, CLAUDE.md, assistant rules, memory files, or…