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.
git clone --depth 1 https://github.com/chrismbryant/claude-journal-mcpWrote 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/chrismbryant/claude-journal-mcp/journal-search)<a href="https://agentmods.dev/commands/chrismbryant/claude-journal-mcp/journal-search"><img src="https://agentmods.dev/badge/commands/chrismbryant/claude-journal-mcp/journal-search/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/commands/chrismbryant/claude-journal-mcp/journal-search"><img src="https://agentmods.dev/badge/commands/chrismbryant/claude-journal-mcp/journal-search.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 | $0.00000 | $0.00397 |
| Opus 5 | $0.00000 | $0.00198 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
journal-search 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 11d 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.
What it actually says
Search Journal
You are helping the user search their journal entries.
Process
-
Get search parameters:
- Query (required): What are they looking for?
- Keywords, technologies, concepts
- Can be partial matches
- Project (optional): Filter to specific project?
- Limit (optional): How many results? (default: 20)
- Query (required): What are they looking for?
-
Use the MCP tool: Call
journal_searchwith parameters:journal_search( query="search terms", project="project-name" (optional), limit=20 (optional) ) -
Present results:
- Show results clearly with IDs
- Highlight relevant matches
- If many results, suggest refining search
- If no results, suggest trying different terms or checking spelling
Search Tips to Share
- Broad terms find more: "auth" finds authentication, authorization, OAuth
- Specific terms find less: "JWT token expiration" is very specific
- Technical terms work well: Language names, framework names, tool names
- Try project filter if working across multiple repos
Examples
Example 1: Technology search
User: "Find entries about React"
→ journal_search(query="React", limit=20)
Example 2: Project-specific
User: "Search for database work in my-api"
→ journal_search(query="database", project="my-api")
Example 3: Concept search
User: "Find anything about performance optimization"
→ journal_search(query="performance optimization")
No Results?
If search returns nothing, suggest:
- Trying broader terms
- Checking if they meant a different word
- Using time-based query instead:
/journal-time - Checking if journal has entries:
/journal-stats
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.
- 11d ago First seen · 64 lines · 0 tokens per session scan A 780dbb83a7b8
journal-search is a command published in the GitHub repository chrismbryant/claude-journal-mcp (6 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 397 tokens. 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
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-export
Export instincts for sharing with teammates or other projects.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
implement
Multi-agent advisory squad workflow for implementing code changes: classify → score risk → select agents → planner → Gate 1 (plan approval) → advisory squad → Gate 2 (Blocker halt) → implementer → consolidator → verdict. Auto-detects depth (quick/normal/deep) from risk + file count; pass --quick or --deep to override.…
vouch
Show RunVouch status of all scheduled agents and open alerts.
analyze-email
Quick analysis of a single email. Read metadata, summarize content, and list attachments.