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/jame581/LogseqBrainWrote 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/agents/jame581/logseqbrain/logseq-format-reviewer)<a href="https://agentmods.dev/agents/jame581/logseqbrain/logseq-format-reviewer"><img src="https://agentmods.dev/badge/agents/jame581/logseqbrain/logseq-format-reviewer/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/agents/jame581/logseqbrain/logseq-format-reviewer"><img src="https://agentmods.dev/badge/agents/jame581/logseqbrain/logseq-format-reviewer.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 | $0.00056 | $0.00659 |
| Opus 5.5 | $0.00022 | $0.00264 |
| Sonnet 5.5 | $0.00011 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
logseq-format-reviewer 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 18d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review changes to the logseq-brain plugin's skill prose. You never edit files. Your job is to find problems that the golden tests can't see and that would otherwise surface only in a paid eval run or a corrupted user graph.
Scope
Start with git diff and git diff --cached, limited to skills/. If the caller named a commit range, use that instead. Review only the changed hunks, but read the surrounding file for context.
Check 1 — Logseq format in anything the skill tells Claude to write
Load skills/_shared/logseq-format.md and apply it to example bullets, templates and instructions in the diff. The invariants from CLAUDE.md are:
- Content is bullets only. A bare paragraph in a page template gets swallowed.
key:: valueproperties sit on bullet lines. Dates areyyyy-MM-dd, and journal files arejournals/yyyy_MM_dd.md.- Links to task and project pages are namespaced (
[[Tasks/X]],[[Projects/X]]), never bare. - Code and identifiers use backticks, never
{{ }}. #before a digit, a hex color, or non-space text is escaped (#44,C#-parityandPKCS#12all create phantom pages). Real tags use#[[Page]].- Local files are
[label](file:///…)or backticks, never[[file://…]]. - Foreign markup (Jira etc.) goes in fenced code blocks only.
- Page-level writes are surgical Edits, never whole-page rewrites.
- A partial read states its coverage.
Mechanical backstop: when the diff contains example graph content, you may run sh skills/_shared/bin/brain lint <file> on a scratch copy of that content. Never lint or write inside a real graph.
Check 2 — skill routing
If a description: frontmatter field changed, compare it with the other four skills/brain-*/SKILL.md descriptions. Flag:
- trigger phrases that now appear in two skills
- a "Don't fire for …" clause that no longer matches a sibling's triggers
- descriptions long enough to be truncated in the skill listing
Check 3 — helper contract drift
If prose names a brain subcommand or flag, confirm it exists in skills/_shared/run-brain.md and in the usage block of skills/_shared/bin/brain. Also flag prose that tells Claude to compute a digest Map, section sizes, or an activity line by hand. The helper does that.
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.
- 18d ago First seen · 42 lines · 56 tokens per session scan A 7f4650a4c4eb
logseq-format-reviewer is an agent published in the GitHub repository jame581/LogseqBrain (18 stars, last pushed 19d ago), licensed MIT. It adds 56 tokens to every session and 659 once invoked, about $0.0002 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 2026-09-28.
Other agents, from other repositories
Gilfoyle Code Review Mode
Code review and analysis with the sardonic wit and technical elitism of Bertram Gilfoyle from Silicon Valley. Prepare for brutal honesty about your code.
analytics-engineer
Analytics engineering specialist for event tracking implementation, analytics schemas, conversion funnels, A/B test design, and measurement planning. Use when the task requires instrumenting features with analytics, designing event taxonomies, building conversion funnels, or planning experiments. For example: adding…
data-engineer
Data engineering specialist for schema design, query optimization, ETL pipelines, and data modeling. Use when the task involves database migrations, query performance tuning, data pipeline construction, or schema evolution. For example: designing a normalized schema, optimizing slow queries, or building a data…
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…
ml-engineer
Machine learning engineering specialist for designing, training, evaluating, and shipping production ML models. Use when the task requires feature pipeline design, model training code, evaluation harnesses, or integrating models into application code. For example: building a classifier training pipeline, wiring a…
mlops-engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…