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 momentmaker/kaijutsu --skill journalgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/momentmaker/kaijutsu/journal)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/journal"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/journal/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/momentmaker/kaijutsu/journal"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/journal.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 | $0.00066 | $0.01726 |
| Opus 5.5 | $0.00026 | $0.00690 |
| Sonnet 5.5 | $0.00013 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00173 |
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 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monthly Development Journal
Generate a structured narrative of what happened in this project over a month. Reads git log, merged PRs, decisions, and any project memory the agent has access to.
Cadences
Default is monthly. Other cadences accept the same data but produce different narratives:
/journal weekly— last 7 days. Lighter narrative; focus on what shipped + what's next./journal sprint— last sprint length (default 14 days; configurable via.claude/journal-cadence.yaml)./journal release— since the last git tag. Releases-as-units narrative./journal monthly(default) — calendar month, full retrospective.
The data-gathering steps (git log, PRs, decisions, memory) are identical; only the time window and narrative emphasis differ.
Step 1: Determine the Window
Resolve the time window by cadence:
| Cadence | Window resolution |
|---|---|
monthly (default) |
Previous calendar month if today is day 1-7, otherwise current month. Argument may be a month name (march) or YYYY-MM. |
weekly |
Previous ISO week if today is Mon/Tue, otherwise current ISO week. Argument may be YYYY-WW. |
sprint |
Last sprint length ending today (default 14 days; configurable via .claude/journal-cadence.yaml). |
release |
Since the most recent git tag (use git describe --tags --abbrev=0). End at HEAD. |
Compute start_date and end_date accordingly. For monthly, start_date = first day of month, end_date = first day of next month. For weekly, ISO week boundaries. For sprint, today minus sprint length. For release, the tag's commit date and HEAD's commit date.
Check if the would-be filename (per Step 6's table) already exists. If so, ask: "A journal for {window-label} already exists. Regenerate it?"
Step 2: Gather Data
Run ALL of the following in parallel:
Git History
git log --oneline --since="{start_date}" --until="{end_date}"— all commitsgit log --since="{start_date}" --until="{end_date}" --format="%H %s" --reverse— commits with hashes for grouping by branchgit shortlog -sn --since="{start_date}" --until="{end_date}"— contributor summary- Detect default branch:
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||'(fallback tomain)
What ships with it
2 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 · 161 lines · 66 tokens per session scan A d6005e40d8f7
journal is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 1,726 once invoked, about $0.0003 per session on Opus 5.5. 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.