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 agentmods add skills/vneel-code/ghost/memory-groundingnpx skills add vNeeL-code/GHOST --skill memory-groundinggit clone --depth 1 https://github.com/vNeeL-code/GHOSTWhat 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 | $0.00017 | $0.00137 |
| Opus 5 | $0.00009 | $0.00068 |
| Sonnet 5 | $0.00003 | $0.00027 |
| Haiku 4.5 | $0.00002 | $0.00014 |
Grade A, and why
memory-grounding 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 2d 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.
What it actually says
Memory & Grounding Skill
Use this skill to remember what the user said in the past or to check your "Diary" for emotional context.
Guidelines
- Call
readDiaryEntries()to see your recent summaries and thoughts. - If the user asks about a specific past event, use your internal memory recall.
- Use
addDiaryEntryto save new significant facts about the user. - Always stay consistent with your previous sovereign states.
Tools Available
- readDiaryEntries
- addDiaryEntry
- getSystemStatus
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.
- 2d ago First seen · 18 lines · 17 tokens per session scan A 1e4bbfeda579
memory-grounding is a skill published in the GitHub repository vNeeL-code/GHOST (162 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 137 once invoked, about $0.0001 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
ii-app
Use this skill when you need to initialize or restart local web and mobile app projects through the bundled Rust ii-app CLI instead of calling MCP tools.
watch-pr
Watch a pushed PR's checks with the Monitor tool, and act on the verdict. Use after opening or pushing to a PR.
device-screenshots
Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens. Use whenever a change is visual - colours, themes, drawables, layout - or when a screenshot needs comparing before and after, light and dark.
watch-gradle-tests
Watch a Gradle instrumented-test run to a verdict without hand-writing greps. Use whenever running :app:testEmulatorDebugAndroidTest or :app:connectedDebugAndroidTest in the background.
Debroid CLI Debugger
Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.
kotlin-multiplatform
Platform abstraction decision-making for Amethyst KMP project. Guides when to abstract vs keep platform-specific, source set placement (commonMain, jvmAndroid, platform-specific), expect/actual patterns. Covers primary targets (Android, JVM/Desktop, iOS) with web/wasm future considerations. Integrates with…