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/terrene-foundation/metis/journalgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/commands/terrene-foundation/metis/journal)<a href="https://agentmods.dev/commands/terrene-foundation/metis/journal"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/journal.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00741 |
| Opus 5 | $0.00008 | $0.00370 |
| Sonnet 5 | $0.00003 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
journal 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage the project journal. The journal is the primary knowledge trail — it captures decisions, discoveries, trade-offs, risks, connections, and gaps across sessions.
Parse $ARGUMENTS:
- Empty or "status": Show journal status
- "new TYPE topic": Create a new journal entry (e.g.,
new DECISION chose-event-driven) - "search QUERY": Search existing entries by topic or tag
Action: Status (default)
-
Determine the active workspace:
- If working in a workspace, use it
- Otherwise, use the most recently modified directory under
workspaces/(excludinginstructions/)
-
In the workspace's
journal/directory:- Count total entries
- Count entries by type (DECISION, DISCOVERY, TRADE-OFF, RISK, CONNECTION, GAP)
- List the 5 most recent entries with their date, type, and topic (from frontmatter)
- Show the highest entry number (for next entry reference)
-
Present as a compact summary.
Action: New Entry
-
Parse the TYPE and topic from arguments. Valid types: DECISION, DISCOVERY, TRADE-OFF, RISK, CONNECTION, GAP.
-
Determine the next sequential number by checking the highest existing
NNNN-prefix in the journal directory. If no entries exist, start at0001. -
Create the file at
journal/NNNN-TYPE-topic.mdwith this structure:
---
type: [TYPE]
date: [today's date, YYYY-MM-DD]
project: [workspace name]
topic: [topic description]
phase: [current COC phase: analyze | todos | implement | redteam | codify | deploy]
tags: []
---
## [Section heading appropriate to type]
[Content — prompt the user for details if not provided]
-
Type-specific structure:
- DECISION: Sections for Decision, Alternatives Considered, Rationale, Consequences
- DISCOVERY: Sections for What Was Discovered, Why It Matters, Follow-Up
- TRADE-OFF: Sections for Trade-Off, What Was Gained, What Was Sacrificed, Acceptable Because
- RISK: Sections for Risk Identified, Likelihood and Impact, Mitigation, Follow-Up
- CONNECTION: Sections for Connection, Components Linked, Why This Matters
- GAP: Sections for What Is Missing, Why It Matters, How to Resolve
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.
- 4d ago First seen · 83 lines · 15 tokens per session scan A b879031bdce3
journal is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 741 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.