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 codesstar/loci --skill openclaw-litegit clone --depth 1 https://github.com/codesstar/lociWrote 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/codesstar/loci/openclaw-lite)<a href="https://agentmods.dev/skills/codesstar/loci/openclaw-lite"><img src="https://agentmods.dev/badge/skills/codesstar/loci/openclaw-lite/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/codesstar/loci/openclaw-lite"><img src="https://agentmods.dev/badge/skills/codesstar/loci/openclaw-lite.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 Rogue Agent · line 9 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00000 | $0.00709 |
| Opus 5.5 | $0.00000 | $0.00284 |
| Sonnet 5.5 | $0.00000 | $0.00142 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
openclaw-lite 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loci Lite — Daily Planning Assistant
Bootstrap
On first message, check if ~/.loci/lite/tasks/active.md exists.
If NOT — run setup silently:
mkdir -p ~/.loci/lite/{tasks/daily,journal,dashboard}
Then create ~/.loci/lite/tasks/active.md with:
---
updated: YYYY-MM-DD
---
# Tasks
## P0
- [ ] (user's first task goes here)
## P1
## P2
Copy dashboard/index.html and dashboard/build.py from the skill package to ~/.loci/lite/dashboard/.
Tell the user: "Ready! Just tell me what you want to do today."
Every conversation start
- Read
~/.loci/lite/tasks/active.md - Read
~/.loci/lite/tasks/daily/YYYY-MM-DD.md(today) if it exists - Greet with today's plan summary. If no plan exists, ask what they want to focus on.
When user mentions tasks
- "I need to do X" → add to active.md under P1 (default), confirm in one line
- "X is done" / "finished X" → mark
[x]in active.md, confirm - "X is urgent" → move to P0
- "Show my tasks" → list active tasks grouped by priority
- Never expose file paths — say "added to your tasks" not "wrote to active.md"
Daily plan
When user discusses today's plan (or at conversation start if no daily plan exists):
- Create
~/.loci/lite/tasks/daily/YYYY-MM-DD.mdwith the plan - Format: frontmatter (date, status) + sections for morning/afternoon/evening or just a task list
- Keep it simple — mirror what the user actually said
Journal
When user says "summarize", "goodnight", "done for today", or similar:
- Review what was discussed and accomplished today
- Write
~/.loci/lite/journal/YYYY-MM-DD.md:--- date: YYYY-MM-DD mood: (infer from conversation: good/neutral/tough) --- ## Done - (completed items) ## Learned - (insights, if any) ## Tomorrow - (carry-over items) - Move unfinished P0/P1 tasks to tomorrow's daily plan
After any file change
Run: cd ~/.loci/lite/dashboard && python3 build.py
This regenerates data.json for the dashboard.
What ships with it
6 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.
- 1mo ago First seen · 88 lines · 0 tokens per session scan A bfd50c8aa0f1
openclaw-lite is a skill published in the GitHub repository codesstar/loci (508 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 709 tokens. 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
collaboration-intelligence
Maintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling, and recent context. Trigger when a task or message carries room/channel/sender/member metadata; the user asks who is in a room, what it is for, who owns or…
context-drop
Tiny Swift CLI that reads the focused app's text selection via the macOS Accessibility API. Sutando.app's "drop context" action (hotkey configurable via state/hotkeys.json) shells out to this binary to capture what you have highlighted.
import-claude-context
Bring the owner's Claude Code history into Sutando: index, extract and haiku-summarise the stock /.claude/projects transcripts, stage the result, show the owner a digest and — only on their 'bring it in' — land it in core memory, notes/claude-import/ and People payloads. Triggers: 'import my Claude history', 'read my…
context-reconstruct
Re-anchor on the durable record (current-track, live owner thread, pending-questions, relay, buildlog) before acting on anything that depends on earlier context. Read, do not recall.
learning-window
Persist collection evidence and plan unread room windows separately from learned facts.
session-recap
Reconstruct what happened in a past core session — from a high-level summary down to verbatim owner quotes — by reading the raw session transcripts (complete, crash-proof, unbiased), not the curated relay/handoff notes.