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 commands/railly/agent-brain/todaygit clone --depth 1 https://github.com/Railly/agent-brainWhat 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 | $0.00014 | $0.01009 |
| Opus 5 | $0.00007 | $0.00504 |
| Sonnet 5 | $0.00003 | $0.00202 |
| Haiku 4.5 | $0.00001 | $0.00101 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-of-day summary: auto-detect commits across repos, merge with manual entries, generate daily log, reflect.
WAVE 0: Gather Data (ALL PARALLEL, one message)
| # | Tool | Call | Purpose |
|---|---|---|---|
| 1 | Bash | Scan repos under ~/Programming for today's commits via git log --oneline --since="today" per repo |
Collect commits |
| 2 | Read | 02_Journal/daily/{TODAY}.md |
Check if log exists (preserve Ship Log entries) |
| 3 | Read | 02_Journal/daily/{YESTERDAY}.md |
Extract uncompleted - [ ] tasks for carry-over |
| 4 | Read | 02_Journal/weekly/week-{YEAR}-W{WEEK_NUM}.md |
Weekly goal + MITs |
Compute dates mentally (you know today's date from system context).
WAVE 1: Show + Ask
- Display auto-detected data summary (repos, commits)
- Show carried-over tasks from yesterday
- Ask: "What else did you do today? (meetings, research, calls, ideas, decisions, learnings)"
- If user says nothing/skip, proceed with auto-detected data only
WAVE 2: Generate Log
Create or UPDATE 02_Journal/daily/{TODAY}.md.
If file already exists
PRESERVE these sections:
## Ship Log(timestamped entries from /log and /ship)- Any manual
- [HH:MM]entries
UPDATE these sections with fresh data:
## Accomplishments## Stats## Projects Touched
Template
---
type: daily
week: "[[week-{YEAR}-W{WEEK_NUM}]]"
rating:
---
# {TODAY} - {Weekday}
## Weekly Goal
{from weekly file, or "No weekly goal set -- run /week"}
## Today's Tasks
- [ ] {from carry-over or user input}
## Pending (from yesterday)
- [ ] {uncompleted tasks from yesterday's log}
## Accomplishments
### {repo} ({n} commits)
1. {commit message -- expand with context}
### Other
1. {user-provided activities}
## Projects Touched
1. **{repo}**: {one-line summary of what changed}
## Content Ideas
{Generate 2-4 SPECIFIC ideas with hooks:}
1. Tweet: "{actual hook text}"
2. Thread: "{topic}" -- {why it's interesting}
## Learnings
1. {specific technical or strategic insight}
## Tomorrow
- [ ] {planned tasks}
## Ship Log
{preserved from existing file}
## Stats
- **Total commits**: {n}
- **Repos touched**: {n} ({list})
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 · 150 lines · 14 tokens per session scan A 4dcde3660934
today is a command published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,009 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.