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 cosmicstack-labs/mercury-agent-skills --skill gbrain-litegit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-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/cosmicstack-labs/mercury-agent-skills/gbrain-lite)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/gbrain-lite"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/gbrain-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/cosmicstack-labs/mercury-agent-skills/gbrain-lite"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/gbrain-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00687 |
| Opus 5 | $0.00014 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
gbrain-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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GBrain Lite — Lightweight Personal Knowledge Base
Organize books, people, concepts, and news items from conversations into a searchable, cross-referenced markdown knowledge base.
Workspace
- Knowledge base directory:
brain/ - Subdirectories by type:
books/people/meetings/ideas/articles/projects/news/ - One entry = one
.mdfile - News entries by date:
news/YYYY-MM-DD/
Workflow
- Trigger check — Book/person/concept/news mentioned in conversation → proactively check brain
- Search — Full-text search in
brain/directory (ripgrep/grep) - Decide
- Existing entry → reference it, update if needed
- No entry + important → create immediately
- No entry + uncertain → ask user
- Create — Write
brain/{type}/{slug}.md- Slug: lowercase/hyphenated
- Must include YAML frontmatter (title, type, date, tags, summary)
- Cross-reference — Update
linksfield in related entries - Sync — Keep key entry index in agent memory
Rules
- Don't dump long content directly into agent memory — prefer brain
- Don't create entries without
titleanddate - Don't skip the
summaryfield — search and listing depend on it - Don't manually write
updated— it auto-updates on save - News entries must use
item_idas dedup key (format:github:owner/repo/hn:12345/arxiv:url) - Don't do full overwrite updates on existing entries — use targeted patches
Validation
- New entry has complete frontmatter (title, type, date, tags, summary)
- Full-text search finds the new entry
- News entries contain
item_id+first_seen+star_history(GitHub entries) - Agent memory usage below 90%, otherwise trigger distillation to brain
Pitfalls
Brain vs Memory confusion
- Symptom: Long-form content consumed all agent memory space
- Root cause: Everything dumped into memory instead of brain
- Fix: >500 chars → brain entry; memory only keeps index pointers. (Fixed: 2026-05-12)
Missing item_id on news entries
- Symptom: Duplicate news entries accumulate, dedup impossible
- Root cause: Agent skipped
item_idfield when creating news entries - Fix: Always include
item_idfor news entries, validated in creation workflow
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.
- 10d ago First seen · 73 lines · 28 tokens per session scan A 504e415310c3
gbrain-lite is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (470 stars, last pushed 15d ago), licensed MIT. It adds 28 tokens to every session and 687 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
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
agent-expert-creation
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…