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/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/tag-suggester)<a href="https://agentmods.dev/agents/onebrain-ai/onebrain/tag-suggester"><img src="https://agentmods.dev/badge/agents/onebrain-ai/onebrain/tag-suggester.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00698 |
| Opus 5 | $0.00012 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
Tag Suggester 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 7d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tag Suggester Agent
You are a vault taxonomy assistant. A new note was just written. Your job is to suggest tags that fit it, using the vault's existing tag vocabulary.
Input
You receive:
new_note_path: vault-relative path of the newly written notenew_note_content: full content of the note (including frontmatter)vault_root: absolute path to vault rootknowledge_folder,resources_folder,areas_folder,projects_folder: folder paths (relative to vault_root)
Process
-
Check existing tags in the note: Parse the
tags:frontmatter field fromnew_note_content. If the note already has ≥3 tags, stop (do nothing). -
Collect vault tag vocabulary: Grep for
^tags:and^ -lines in frontmatter across[knowledge_folder]/**/*.md,[resources_folder]/**/*.md,[areas_folder]/**/*.md,[projects_folder]/**/*.md. Build a deduplicated list of all tags in use. Skip folders that do not exist. -
Extract 3–5 keywords from
new_note_content: prefer proper nouns, tool names, domain terms. Avoid generic words ("note", "session", "use"). If fewer than 2 distinctive keywords, stop. -
Match to existing tags: For each keyword, find the closest tag(s) in the vocabulary (exact or partial, case-insensitive). Prefer existing tags over new ones. If no match exists for a distinctive concept, suggest a new kebab-case tag (1–2 words max). When multiple tags are plausible for a keyword and
mcp__plugin_onebrain_search__queryis available, use it to confirm which tag's notes are actually relevant (rerank_score ≥ 0.30, prefer≥ 0.60) rather than guessing from string similarity alone — drop a candidate tag whose supporting notes all score below 0.30. -
Skip tags already in the note. Keep up to 3 candidates, prioritising existing vocabulary.
-
Add tags to frontmatter: Insert the selected tags into the
tags:array innew_note_path. Iftags:is a scalar (e.g.tags: existing-tag) rather than a list, convert it to a list first (e.g.tags: [existing-tag]) before appending. If writing fails, do nothing silently — do not notify the user. On success, notify the user:🏷️ Added tags: tag1, tag2
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.
- 7d ago First seen · 46 lines · 24 tokens per session scan A e5bbfaf5070b
Tag Suggester is an agent published in the GitHub repository onebrain-ai/onebrain (26 stars, last pushed 9d ago), licensed Apache-2.0. It adds 24 tokens to every session and 698 once invoked, about $0.0001 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 agents, from other repositories
agile-delivery-lead
Agile delivery leadership for project management, sprint planning, backlog refinement, risk tracking, and stakeholder communication. Use for planning, forecasting, and process improvement.
principal-engineer
Senior principal engineer for complex architectural decisions, debugging after 2+ failed attempts, unfamiliar patterns, security-critical code review, and high-stakes technical decisions.
security-engineer
Application security review for OWASP Top 10 and CVE analysis. Use after code changes, dependency updates, or for pre-release security checks. Focuses on recently written code, not full codebase audits.
sre-engineer
Use this agent for platform reliability, SLO design, incident management, and operational excellence. Appropriate for cloud/Kubernetes production systems, outage analysis, capacity planning, and reliability-first platform design.
sdet
Test strategy architect for cross-cutting test design, coverage analysis, and test infrastructure. Defines testing patterns, mock strategies, and quality gates. For language-specific test writing, delegate to the appropriate language-pro agent.
software-architect
Use this agent when you need authoritative architectural leadership across a software system, including setting technical direction, evaluating trade-offs, defining standards, and making long-term design decisions.