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 skills/iamlukethedev/hermes3d/task-managernpx skills add iamlukethedev/Hermes3D --skill task-managergit clone --depth 1 https://github.com/iamlukethedev/Hermes3DWrote 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/iamlukethedev/hermes3d/task-manager)<a href="https://agentmods.dev/skills/iamlukethedev/hermes3d/task-manager"><img src="https://agentmods.dev/badge/skills/iamlukethedev/hermes3d/task-manager.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 | $0.00056 | $0.01403 |
| Opus 5 | $0.00028 | $0.00701 |
| Sonnet 5 | $0.00011 | $0.00281 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
task-manager 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 4d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Manager
Use this skill for task capture and task lifecycle updates.
Trigger
{
"activation": {
"anyPhrases": [
"add a task",
"create a task",
"track this task",
"task status",
"mark this done",
"block this task",
"what tasks do we have"
]
},
"movement": {
"target": "desk",
"skipIfAlreadyThere": true
}
}
Also use this skill even when those exact phrases are absent if the latest user message is an actionable work request. If the user asks the agent to do something, that request must become a task before the agent proceeds.
Storage location
The authoritative task file is:
${HERMES_STATE_DIR}/hermes3d/task-manager/tasks.jsonwhenHERMES_STATE_DIRis set.~/.hermes/hermes3d/task-manager/tasks.jsonotherwise.
Always treat that file as the shared source of truth for the Kanban board.
Required workflow
- Read the task file before handling an actionable request.
- If the file does not exist, create it with the schema in this document.
- If the latest user message is actionable and no matching active task exists, create one immediately.
- Before starting execution, move the task from
inboxtoworking. - If work is blocked on a human (command approval, missing input, credentials, or an error), set the task to
needs_attentionand record a short reason innotes. - When work is finished, set the task to
done. - When a task is queued by the cron scheduler or a playbook for a later run, keep it in
scheduledand setscheduledFor. - After every mutation, write the full updated JSON back to disk.
Matching rules
- Match first by
externalThreadIdwhen the request comes from a stable thread or conversation. - Otherwise match by a concise normalized title that preserves user intent.
- Avoid creating duplicate active tasks for the same request.
Task fields
Each task must include:
idtitledescriptionstatussourcesourceEventIdassignedAgentIdcreatedAtupdatedAtplaybookJobIdrunIdchannelexternalThreadIdlastActivityAtnotesisArchivedisInferredmodelskillssubagentCountscheduledForlearnedSkillhistory
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 165 lines · 56 tokens per session scan A ae2da229c291
task-manager is a skill published in the GitHub repository iamlukethedev/Hermes3D (337 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,403 once invoked, about $0.0003 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 skills, from other repositories
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
todo
Maintain a shared workspace TODO list with blocked tasks.
soundclaw
Control Spotify playback, search music, and return shareable music links.
claim-issue
Atomically claim an issue for a developer (human or agent) via the cross-developer lock ref, so two devs never pick up the same task. Syncs with origin first, refuses if already claimed or already done on main, and pushes the claim immediately without touching main or triggering CI.
create-issue
Create a new issue file from a test262 failure pattern. Includes smoke test, sample extraction, and proper frontmatter.
sprint-planning
Collaborative sprint planning — validate issues, prioritize, get architect/SM input, create task queue. Any agent can facilitate.