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 cyrus-cai/claude-cobrain --skill todaygit clone --depth 1 https://github.com/cyrus-cai/claude-cobrainWrote 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/cyrus-cai/claude-cobrain/today)<a href="https://agentmods.dev/skills/cyrus-cai/claude-cobrain/today"><img src="https://agentmods.dev/badge/skills/cyrus-cai/claude-cobrain/today/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/cyrus-cai/claude-cobrain/today"><img src="https://agentmods.dev/badge/skills/cyrus-cai/claude-cobrain/today.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00011 | $0.01253 |
| Opus 5 | $0.00005 | $0.00626 |
| Sonnet 5 | $0.00002 | $0.00251 |
| Haiku 4.5 | $0.00001 | $0.00125 |
Grade A, and why
today scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
today
Generate an actionable daily insight briefing — not a logbook.
Phase 1: Locate and Profile the Data
- Resolve output directory (direct python mode):
OUTPUT_DIR="${OUTPUT_DIR:-$HOME/.claude/cobrain}"
echo "$OUTPUT_DIR"
- Build today's file path and check existence:
OUTPUT_DIR="${OUTPUT_DIR:-$HOME/.claude/cobrain}"
TODAY_FILE="$OUTPUT_DIR/$(date +%Y%m%d)-raw.md"
test -f "$TODAY_FILE" && echo "exists" || echo "missing"
- If the file does not exist or is empty, report:
- "No cobrain entries captured today. The daemon may not be running — check with
status." - Stop here.
- "No cobrain entries captured today. The daemon may not be running — check with
Phase 2: Efficient Metadata Extraction (bash-first)
CRITICAL: Do NOT read the raw file yet. Use bash/grep to extract structured metadata first. This avoids wasting tokens on repetitive VLM output and <think> blocks.
- Extract entry count, time range, and per-app frequency:
# Entry count and time range
echo "=== ENTRY COUNT ==="
grep -c '^### ' "$TODAY_FILE"
echo "=== FIRST ENTRY ==="
grep -m1 '^### ' "$TODAY_FILE"
echo "=== LAST ENTRY ==="
grep '^### ' "$TODAY_FILE" | tail -1
echo "=== APP FREQUENCY ==="
grep '^### ' "$TODAY_FILE" | sed 's/^### [0-9:]\+ · //' | sort | uniq -c | sort -rn
- Identify distinct activity blocks — consecutive runs of the same app represent a single work session:
# Show app transitions (block boundaries) with timestamps
grep '^### ' "$TODAY_FILE" | awk -F ' · ' '{app=$2} app!=prev {print NR, $0; prev=app}'
This gives you the session structure: how many blocks, what sequence of activities, and approximate durations.
Phase 3: Intelligent Content Sampling
-
For each distinct activity block (consecutive same-app entries), read ONLY the first and last entry to understand what that session was about. This achieves full activity coverage at ~10% token cost.
- Use
grep -nto find line numbers of block boundaries - Use
Readtool with offset/limit to read only those specific entries (typically 5-10 lines each) - For very short blocks (1-2 entries), reading the single entry is sufficient
- Never read the entire file
- Use
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 · 132 lines · 11 tokens per session scan A 679d2668b399
today is a skill published in the GitHub repository cyrus-cai/claude-cobrain (5 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,253 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 2026-08-31.
Other skills, from other repositories
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Tool-agnostic in design but defaults to a vault at…
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…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
claude-md-updater
Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. Use for save this lesson or add to context.