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-resume-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-resume-task)<a href="https://agentmods.dev/skills/bonnguyenitc/specship/ss-resume-task"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-resume-task/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.
<a href="https://agentmods.dev/skills/bonnguyenitc/specship/ss-resume-task"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-resume-task.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00092 | $0.02307 |
| Opus 5 | $0.00046 | $0.01154 |
| Sonnet 5 | $0.00018 | $0.00461 |
| Haiku 4.5 | $0.00009 | $0.00231 |
Grade A, and why
ss-resume-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 10d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Task
Goal: given little or no context, re-enter an existing task — find it, reconstruct where it stands from the on-disk state, and hand off to the right stage skill so work continues without redoing finished stages.
Task state lives on disk (tasks/TASK-<ID>/), not in the chat session — that's exactly what makes resuming possible. This skill turns that durable state back into momentum.
ss-resume-task is an entry point, not a stage: it doesn't produce its own artifact. It reads the shared state, reports it, and invokes the correct stage skill. It's the interactive counterpart to ss-ship — where ss-ship auto-advances every handoff, ss-resume-task resumes one stage and then follows the normal per-stage checkpoints (ask before advancing).
When to use
- You're starting a fresh session and want to continue a task already underway.
- After a context reset, an interruption, or switching away and back.
- The user asks where a task stands, or to "continue / pick up / resume" — and you need to reconstruct state before acting.
- Not for starting new work (use
ss-spec/ss-ship) and not for mapping an unfamiliar codebase (usess-explore-source).
Shared task state
Part of the task pipeline — see ../WORKFLOW.md for the full contract. ss-resume-task reads the shared state and delegates; the stage skill it invokes does the writing.
- Hydrate: read
tasks/LESSONS.mdif present (apply its rules) and the target task'stask.md+ its artifacts (below). - Checkpoint:
ss-resume-taskwrites totask.mdonly to (a) un-shelve a task it's resuming (flippaused→active, or move a folder back out ofarchive/— see step 1) or (b) repair a missing trace while reconstructing state (see../WORKFLOW.md→ Flow integrity). Both bumpupdated:and add a dated Pipeline Log line carrying your agent label (format:../WORKFLOW.md→ Agent handoff); it never touchesstage/artifacts:. All pipeline checkpointing is the resumed stage skill's job.
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.
- 10d ago First seen · 81 lines · 92 tokens per session scan A 26a438e5340d
ss-resume-task is a skill published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,307 once invoked, about $0.0005 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
waku-computer-use
Control local Mac apps through Waku Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.
save
Lightweight incremental checkpoint for a long autonomous run — refresh the handoff, commit converged work, and push, fired frequently (after each subagent merge, periodically, and when nearing the rate-limit → then ScheduleWakeup past the window reset). Complements /pause (deliberate one-shot handoff) and /resume (the…
statusline
Configure model, context, and usage status display: Codex uses its built-in statusline picker; Claude Code uses bin/install-statusline.sh. Turn the status line on or off without clobbering other settings.
voice-chat
Hands-free voice chat via Claude Code or Codex CLI, whisper.cpp transcription, and local TTS (say, espeak, Piper, XTTS). Set up or run the headphones-only voice loop on macOS, Linux, or WSL.
loop
Schedule recurring work, inspect or stop loops, and route user steering to an active main-orchestrator loop by default; portable macOS/Linux/WSL/Windows driver.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.