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 skills/backspace-shmackspace/claude-devkit/journalnpx skills add backspace-shmackspace/claude-devkit --skill journalgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.00078 | $0.03846 |
| Opus 5 | $0.00039 | $0.01923 |
| Sonnet 5 | $0.00016 | $0.00769 |
| Haiku 4.5 | $0.00008 | $0.00385 |
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 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 — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/journal Workflow
Inputs
User provides:
- Natural language description of what to journal (content, context, topic)
- Optional: explicit entry type (daily, meeting, project, learning, decision)
- Optional: project name, topic name, or meeting title
Scope parameters:
JOURNAL_BASE:~/journal/(hardcoded, user can modify in skill file if needed)TEMPLATES_DIR:~/journal/templates/(on-disk templates override embedded defaults)- Supported entry types: daily, meeting, project, learning, decision, biweekly-update
Step 0 — Determine Entry Type
Action: Classify user input to determine which journal entry type to create.
Classification rules:
- daily: User mentions "daily", "today", "log", "work session", or provides general work update without specific meeting/learning/decision context
- meeting: User mentions "meeting", "standup", "sync", "call", or references attendees/agenda
- project: User mentions "project update", references a specific project name, or provides progress on a named initiative
- learning: User mentions "learned", "discovered", "figured out", "TIL", "gotcha", or describes technical insight
- decision: User mentions "decision", "ADR", "decided to", "chose", "picked", describes options/tradeoffs
- biweekly-update: User mentions "biweekly", "bi-weekly", "PSLT update", "leadership update", "14-day update", "fortnightly", or "status update for leadership"
Disambiguation heuristic:
- If input matches multiple types, default to broader type: daily > project, meeting > decision
- A decision made in a meeting goes in the meeting entry unless user explicitly wants separate ADR
- If still ambiguous after heuristic, ask user to clarify
Deprecated types:
- If user says "idea" or "todo", explain these are now captured in daily notes (
## Learningsfor ideas,## Tomorrow's Prioritiesfor todos) and offer to add content there - Do not silently fail or ignore deprecated types
Tool declarations: Read (to check existing files), Bash (for date operations)
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 · 533 lines · 78 tokens per session scan A ae3ee4ce9a22
journal is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 3,846 once invoked, about $0.0004 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
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
worktree-switching
Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-fresh-verifier
L4 blind fresh verifier - independently checks a candidate roadmap or plan against the exact mission and repository; APPROVE/REJECT, default-FAIL.
cron
Schedule reminders and recurring tasks.
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.