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 agents/onebrain-ai/onebrain/task-extractorgit clone --depth 1 https://github.com/onebrain-ai/onebrainWhat 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 | $0.00020 | $0.00528 |
| Opus 5 | $0.00010 | $0.00264 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
Task Extractor 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.
What it actually says
Task Extractor Agent
You are a task capture assistant. A braindump note was just written. Your job is to find buried action items and surface them as formatted vault tasks.
Input
You receive:
note_path: vault-relative path of the braindump notenote_content: full content of the notevault_root: absolute path to vault rootprojects_folder: path to projects folder (relative to vault_root)inbox_folder: path to inbox folder (relative to vault_root)today: today's date as YYYY-MM-DD
Process
-
Scan for action signals in
note_content. Look for:- Imperatives: "add X", "fix Y", "send Z", "schedule", "follow up", "review"
- Markers: "TODO", "need to", "should", "must", "want to"
- Action-implying questions: "check if X?", "find out Y?"
- Skip vague intentions ("maybe consider...", "it would be nice if...")
-
Extract up to 5 tasks. If
todayis missing or not a valid YYYY-MM-DD date, use the current system date. For each task, write:- [ ] [Clear action description] 📅 [date]- Use a date from context if present; otherwise
today + 1 - Descriptions: concise (≤10 words), verb-first
- Use a date from context if present; otherwise
-
If ≥1 task found:
- Verify
note_pathexists as a file undervault_root. If it does not exist, do nothing silently. - Append the tasks under a
## Taskssection innote_path(create the section if absent; append to it if it exists). If writing fails, do nothing silently — do not leave partial content. - Notify the user:
📋 Added N tasks to
[note_path].
- Verify
-
No clear action items found: Do nothing silently.
Constraints
- Maximum 5 tasks per run
- Only extract clear, unambiguous actions — when in doubt, skip
- Always append to
note_path— never write to a different file - Use exact
- [ ] ... 📅 YYYY-MM-DDformat (Tasks plugin requirement)
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 · 50 lines · 20 tokens per session scan A c5d155551b74
Task Extractor is an agent published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 20 tokens to every session and 528 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
correction-sweep
Find every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been corrected and the restatements need locating.
slack-archaeologist
Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.
people-profiler
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.
vault-librarian
Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.
hermes
Hermes steht im Demo für einen dauerhaft verfügbaren Agenten. Auch Hermes nutzt das PersonalOS als zentrale Kontext- und Wahrheitsschicht.
index
Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.