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 skills add bonnguyenitc/specship --skill ss-pause-taskgit clone --depth 1 https://github.com/bonnguyenitc/specshipWrote 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/bonnguyenitc/specship/ss-pause-task)<a href="https://agentmods.dev/skills/bonnguyenitc/specship/ss-pause-task"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-pause-task.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 | $0.00089 | $0.01084 |
| Opus 5 | $0.00044 | $0.00542 |
| Sonnet 5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
ss-pause-task 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 6d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pause Task
Goal: shelve a task on purpose — record that it's intentionally set aside (status: paused) with a reason, while preserving its pipeline stage and every artifact exactly as they are, so ss-resume-task can pick it up later with zero loss.
paused is a deliberate choice, distinct from blocked (stuck on an external dependency, not by choice) and from done (finished). ss-pause-task is a lifecycle skill, not a stage: it touches only status and the log — never stage or artifacts:. It's the inverse of ss-resume-task.
When to use
- You're stepping away from a task and want it clearly marked so it isn't mistaken for active work, and isn't auto-picked when resolving "the current task".
- The user asks to pause / park / hold a task.
- Not for tasks stuck on a dependency (that's just
status: blocked, set by the stage skill) and not for finished work (usess-archive-task).
Shared task state
Part of the task pipeline — see ../WORKFLOW.md → "Task lifecycle". Unlike ss-resume-task, this skill does write tasks/ — that's its job.
Method
Input: an optional task id argument in any form (pause-task TASK-20260723-fix-login, pause-task fix-login, pause-task 007), normalized to the on-disk folder name TASK-<ID>: a full TASK-… id as written; a bare all-digit argument maps to a legacy numeric folder matched as written (don't re-pad or strip leading zeros — 7 and 007 both resolve to TASK-007 if that's the folder); anything else (a slug fragment, or a ticket key like PROJ-123) resolves against tasks/TASK-* and tasks/archive/TASK-* folder names — an exact match (TASK-<argument>) wins, else a unique substring match; several matches → list candidates and ask; none → say so and stop — never fall back to auto-picking another task. A match under tasks/archive/ is already shelved: report it and suggest resume-task <ID> — don't mutate it. No argument → resolve the current task (below).
- Locate the task: the normalized id argument, one named in conversation, else the most-recently-
updated:task undertasks/TASK-*(skiptasks/archive/*and anystatus: pausedtask — already-shelved tasks aren't auto-picked). If several are active or it's ambiguous, list candidates and ask — don't guess. - Check it's pausable: the task must be
activeorblocked. If it's alreadypaused, say so and stop. If it'sdone, suggestss-archive-taskinstead. - Get the reason: use the reason the user gave; if none, ask one line ("Tạm dừng vì lý do gì?") so the pause is self-explanatory later. Don't invent one.
- Write the state in
tasks/TASK-<ID>/task.md— get the real time first (date "+%Y-%m-%d %H:%M %Z"):- set
status: paused; leavestageand everyartifacts:value untouched. - bump
updated:. - in the Now block, note it's paused and why (e.g.
- Blocked by: none (paused — waiting on design)). - Snapshot the working tree: check
git status— if this task's work sits uncommitted, list the mid-flight files in the Now block (e.g.- In flight: src/auth.ts, src/auth.test.ts (uncommitted)), so resuming doesn't mistake them for another task's changes. Suggest the user stash or WIP-commit before switching tasks — don't run git yourself. - append a dated Pipeline Log line:
- <YYYY-MM-DD HH:MM +TZ> paused: <reason>— carrying your agent label (format:../WORKFLOW.md→ Agent handoff).
- set
- Confirm to the user: which task, what stage it's frozen at, and that
/ss-resume-task <ID>brings it back exactly here.
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.
- 6d ago First seen · 37 lines · 89 tokens per session scan A e9652ec2b97f
ss-pause-task is a skill published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 28d ago), licensed MIT. It adds 89 tokens to every session and 1,084 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
summarize
Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.
cyrus-setup-linear
Create a Linear OAuth application and configure Cyrus to use it — supports agent-browser automation or guided manual setup.
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
chat
Conversational assistant for messaging-platform threads (Slack, Discord). Answer questions about repos, PRs, and issues, explain code, and guide users to the natural-language workflow triggers listed in the system prompt.
queue
A visible, editable Markdown work queue that agents drain autonomously — one task at a time or fanned out across parallel git worktrees — running each as a quick chore or the full feature-chain (design→prd→tdd→refine) with no user input. Use to queue, prioritize, stop/restart, seed from in-memory items, or…