task-pause

A command for setting an active task aside while keeping its GitHub issue open for later continuation.

In plain words
What is it for?
Use it when switching to another task without marking the current work complete. It supports selecting a specific issue when multiple tasks are active.
Why use it?
It records the paused issue locally and posts a pause notice before removing it from the active-task list, so the task can be resumed without losing track of it.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/koroqe/opos/task-pause
Any agent
npx skills add Koroqe/OPOS --skill task-pause
Clone the repo
git clone --depth 1 https://github.com/Koroqe/OPOS

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,648 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01648
Opus 5 $0.00017 $0.00824
Sonnet 5 $0.00007 $0.00330
Haiku 4.5 $0.00003 $0.00165

Measured yesterday against content hash 68bfcb5fde0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

task-pause scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **No active task** — `.current-task` absent. Recovery: nothing to pause; user can list paused tasks via `cat .claude/.paused-tasks`.
.claude/skills/task-pause/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task-pause

When to use

When you want to set the current task aside to work on something else, without closing the GitHub issue. The paused issue is recorded in .claude/.paused-tasks for later resumption via task-resume. Replaces the "manually rm .current-task and remember the issue number" workaround that's been used 4× across prior releases.

Inputs

  • issue — optional override. As of v0.7.0 .current-task is a newline-delimited array; this skill auto-picks when exactly 1 is active and REQUIRES --issue when 2+ are active (see step 2).

Steps

ORDER MATTERStask-update (step 3) must run BEFORE the issue is removed from .current-task (step 5), because task-update reads .current-task to know which issue to comment on. Reversed order = task-update may pick the wrong target (or fail if this was the only active task).

  1. Resolve repo root. REPO_ROOT=$(git rev-parse --show-toplevel).

  2. Read .current-task as a newline-delimited array (v0.7.0 array semantics; v0.6.x single-task content parses as 1-element array — fully backwards-compatible). Apply defensive read-side filtering (drop non-digit lines per Risk 30). Then determine the target issue:

    • If --issue <N> was provided → use it directly. (Must be present in the array; if absent, ABORT with Issue #N not in active list. Active: #<list>.)
    • Else if the array has EXACTLY 1 entry → use it (v0.6.x single-task workflow preserved).
    • Else if the array has >1 entries → ABORT with Multiple active tasks: #<comma-list>. Pass --issue <N> to specify which one to pause.
    • Else (empty/absent) → ABORT with "No active task to pause." Capture as $ISSUE. Do not modify .current-task here — the removal happens at step 5 AFTER step 3's task-update has run.
  3. Post pause notice via task-update (while .current-task still exists so task-update can read it):

    task-update \
      --message "Task paused by user; will resume via /task-resume $ISSUE." \
      --key "paused-$(date -u +%Y%m%dT%H%M%SZ)" \
      --status blocked
    

    Why --status blocked not --status paused: task-update's allowed-status set is in_progress | blocked | review. "Paused" is a framework-internal state tracked via .paused-tasks membership; on GitHub the issue shows **Status:** blocked (the closest existing semantic — blocked-by-other-priorities, awaiting resume).

Read the full file on GitHub · 92 lines

Files

What ships with it

2 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.

  1. yesterday First seen · 92 lines · 35 tokens per session scan B 68bfcb5fde0a

Subscribe to this mod's changes

task-pause is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 1,648 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

super-evolve

Ultimate self-evolution skill. Merges evolve + self-improve into one comprehensive meta-skill with external research, area focus, dry-run mode, and expanded memory mining.

OZmasterAI/Torus-Framework · 35 tokens

pr-to-video

Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…

heygen-com/hyperframes · 104 tokens

motion-graphics

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…

heygen-com/hyperframes · 139 tokens

implementation-final-review

Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…

openai/openai-agents-python · 58 tokens

hyperframes-core

The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md…

heygen-com/hyperframes · 77 tokens

captions-overlay

Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether…

heygen-com/hyperframes · 136 tokens