A coordination skill for finding, reading, messaging, delegating, continuing, and stopping durable agent tasks. A Thread is a persistent task address and history that can continue across runs.

Use it to delegate work, send updates, continue finished tasks, or cancel unwanted assignments.

It keeps independent work organized and preserves context when a task needs to continue later or be handled by another agent.

threads — Skill for Codex by steerlabs/opensteer

Install

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.

Any agent

npx skills add steerlabs/opensteer --skill threads

Clone the repo

git clone --depth 1 https://github.com/steerlabs/opensteer

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/steerlabs/opensteer/threads/github.svg)](https://agentmods.dev/skills/steerlabs/opensteer/threads)

Your own site

<a href="https://agentmods.dev/skills/steerlabs/opensteer/threads"><img src="https://agentmods.dev/badge/skills/steerlabs/opensteer/threads/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/steerlabs/opensteer/threads"><img src="https://agentmods.dev/badge/skills/steerlabs/opensteer/threads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 518 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00020	$0.00518
Opus 5.5	$0.00008	$0.00207
Sonnet 5.5	$0.00004	$0.00104
Haiku 4.5	$0.00002	$0.00052

Measured today against content hash 6371d642d813, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

threads 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 today.

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.

apps/runner/agent-skills/skills/threads/SKILL.md · 40 lines

What it actually says

Threads and tasks

A Thread holds durable history; a Run is one execution. Use native workers for Run-local work, thread_delegate for independent work or durable continuation. Give the outcome, context, constraints and completion criteria. Use workspaceId for a new task (or a ready specialist), threadId to continue a finished one. Reuse keeps its engine/model.

Runs and programs get an Assignment and its final result automatically. In a Run, do independent work or end your turn for continuation; thread_wait is absent. Connections get no Assignment or automatic return: keep thread.id, observe with thread_wait and thread_read. Programs may also use thread_wait. A wait timing out or disconnecting never stops the work.

A pending durable Request permits independent work; end your turn when none remains. Never poll, repeat or route around it.

thread_message: report saves passive context; queue asks for a next turn; steer changes a compatible active Run. Accepted is not read; cancelled will not execute.
thread_read: inspect execution selectors and queued inputs with their allowed actions.
thread_configure: set an existing Thread's engine/model/options. Discover exact choices with environment_list when available. Access mode stays; never substitute after refusal.
thread_queue: cancel/move waiting inputs by messageId, steer with expectedRunId, or resume. Preserve a person's pause unless told to resume.
thread_write interrupt: stop the current Run and pause a work queue, keeping pending inputs.
assignment_cancel: Run-only permanent cancellation of an Assignment and its descendants, including Requests and continuations. Confirm the returned status.

Delegation inherits its root's reach; resource grants and access ceilings still apply. On an Assignment, person_message/person_show are refused even when listed. Send distinct earlier news to the assigner (queue if they should act/tell the person); your final reply returns automatically.

Read coordination for selection, discovery and forwarded places; lifecycle for results and blockers; show to show places; Chat/history for earlier context; apps to publish or call an app.

Files

What ships with it

6 files 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.

Changes

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.

today Changed 6371d642d813
yesterday Changed · +11 lines · -1 tokens per session ac435e279bf1
2d ago First seen · 29 lines · 21 tokens per session scan A 65737b096617

Subscribe to this mod's changes

threads is a skill published in the GitHub repository steerlabs/opensteer (204 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 518 once invoked, about $0.0001 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 2026-11-04.

Project management TypeScript ai-agents automation open-source self-hosted

threads next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
threadssteerlabs/opensteer	Skill	204	today	MIT	A	20	Codex
n8n-clin8n-io/n8n	Skill	210k	yesterday	none	A	55	Claude Code
data-table-managern8n-io/n8n	Skill	210k	yesterday	none	A	116	Claude Code, Codex
progressive-buildingn8n-io/n8n	Skill	210k	yesterday	none	A	135	Claude Code, Codex
commonlyTeam-Commonly/commonly	Skill	1.4k	today	Apache-2.0	A	0	Claude Code, Codex
pod-chat-toneTeam-Commonly/commonly	Skill	1.4k	today	Apache-2.0	A	0	Claude Code, Codex
pandic-officeTeam-Commonly/commonly	Skill	1.4k	today	Apache-2.0	A	59	Claude Code, Codex