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 backspace-shmackspace/claude-devkit --skill journal-recallgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWrote 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/backspace-shmackspace/claude-devkit/journal-recall)<a href="https://agentmods.dev/skills/backspace-shmackspace/claude-devkit/journal-recall"><img src="https://agentmods.dev/badge/skills/backspace-shmackspace/claude-devkit/journal-recall/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/backspace-shmackspace/claude-devkit/journal-recall"><img src="https://agentmods.dev/badge/skills/backspace-shmackspace/claude-devkit/journal-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00087 | $0.01805 |
| Opus 5.5 | $0.00035 | $0.00722 |
| Sonnet 5.5 | $0.00017 | $0.00361 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
journal-recall 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/journal-recall Workflow
Inputs
User provides:
- Natural language query describing what to find (date, keyword, topic, project, etc.)
- Optional: date range, entry type filter, project name
Scope parameters:
JOURNAL_BASE:~/journal/(hardcoded, matches /journal skill)- Entry types: daily, meetings, projects, learnings, decisions
- Search modes: date lookup, date range, keyword search, topic search, project filter, weekly review
Step 0 — Classify Intent
Action: Determine what type of retrieval the user wants.
Intent classification:
- Specific date lookup: User mentions a date ("yesterday", "Feb 23", "2026-02-22", "last Tuesday")
- Date range: User mentions a span ("this week", "last month", "between X and Y")
- Keyword search: User provides search terms ("worktree isolation", "Docker socket")
- Topic/project: User asks about a specific topic or project ("what did I do on claude-devkit?")
- Meeting lookup: User asks about meetings ("what meetings did I have?", "standup notes")
- Weekly review: User asks for a summary ("summarize this week", "weekly review", "what happened this week")
- Project status: User asks about a project's current state ("what's the status of X?", "where am I on X?")
Disambiguation:
- If intent unclear, default to keyword search across all entries
- For time-based queries, resolve relative dates ("yesterday" = YYYY-MM-DD, "this week" = past 7 days)
Tool declarations: Bash (date calculations for relative dates)
Output: Search intent classification and search parameters
Step 1 — Retrieve Entries
Action: Use appropriate tools to find and read matching journal entries.
Retrieval strategies by intent:
Specific date lookup:
- Read
daily/YYYY-MM-DD.mddirectly - If date is in past and daily entry doesn't exist, report "No daily entry for YYYY-MM-DD"
- Also check for meetings/decisions on that date using Glob:
meetings/YYYY-MM-DD-*.md,decisions/YYYY-MM-DD-*.md
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 · 184 lines · 87 tokens per session scan A 876cd045e919
journal-recall is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,805 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 2026-08-30.
Other skills, from other repositories
capture-to-vault
Use during /research, /scope (or any recipe) to write or update a vault note via dossier-mcp. Agent drafts slug + frontmatter + body + citations, writes the note, and surfaces what was captured so the user can redirect afterward. Supports create (new note) and update (refine existing note) modes.
load-context
Use at the start of /research and other workflow recipes to establish vault grounding. Loads vault bootstrap (profile.md), checks inbox, and pre-warms project context if a topic anchor is implied. Repo/git detection lands with /plan and /implement.
golang-security
Security best practices and vulnerability prevention for Golang. Covers injection (SQL, command, XSS), cryptography, filesystem safety, network security, cookies, secrets management, memory safety, and logging. Apply when writing, reviewing, or auditing Go code for security, or when working on any risky code involving…
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.