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/koroqe/opos/task-resumenpx skills add Koroqe/OPOS --skill task-resumegit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/task-resume)<a href="https://agentmods.dev/skills/koroqe/opos/task-resume"><img src="https://agentmods.dev/badge/skills/koroqe/opos/task-resume.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 | $0.00034 | $0.01254 |
| Opus 5 | $0.00017 | $0.00627 |
| Sonnet 5 | $0.00007 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade B, and why
task-resume scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. **Verify `issue_number` appears in `.paused-tasks`.** `grep -qx "$ISSUE_NUMBER" "$REPO_ROOT/.claude/.paused-tasks"` else abort: "Issue #$ISSUE_NUMBER not found in paused list." How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-resume
When to use
After task-pause has set a task aside, to bring it back as an active task. As of v0.7.0, .current-task is a newline-delimited array — multi-active tasks are first-class. You can resume a paused task while other tasks are still active; the resumed issue is appended to the existing .current-task array. (Pre-v0.7.0 the framework required .current-task to be absent; that guard is removed.)
Inputs
issue_number— the issue number of the paused task to resume. Required.
Steps
ORDER MATTERS — .current-task must be updated BEFORE task-update is called (step 6 reads it to determine the active task list).
-
Resolve repo root.
REPO_ROOT=$(git rev-parse --show-toplevel). -
Read
.current-taskas a newline-delimited array (v0.7.0). Apply defensive read-side filtering. Multi-active tasks are first-class as of v0.7.0 — the pre-v0.7.0 "verify absent" guard is REMOVED. The only check here is: is$ISSUE_NUMBERalready in the array? If yes → abort with "Issue #$ISSUE_NUMBER already active." If no → proceed. (Defensive against re-running task-resume on an already-resumed issue.) -
Verify
issue_numberappears in.paused-tasks.grep -qx "$ISSUE_NUMBER" "$REPO_ROOT/.claude/.paused-tasks"else abort: "Issue #$ISSUE_NUMBER not found in paused list." -
Remove the matching line from
.paused-tasks. Usegrep -vto a temp file then move into place to avoid in-place-edit portability concerns:grep -vx "$ISSUE_NUMBER" "$REPO_ROOT/.claude/.paused-tasks" > /tmp/paused.tmp && \ mv /tmp/paused.tmp "$REPO_ROOT/.claude/.paused-tasks"If
.paused-tasksis empty after removal, leave it as an empty file (don't delete — keeps the convention discoverable). -
Append
issue_numberto.current-task(v0.7.0 array semantics; replaces the v0.6.x overwrite-single-line behavior):echo "$ISSUE_NUMBER" >> "$REPO_ROOT/.claude/.current-task". Trailing newline IS now used (matchestask-registerstep 10's append convention; the defensive read filter handles either). Other active tasks (in the multi-active workflow) are untouched.
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.
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.
- 5d ago First seen · 72 lines · 34 tokens per session scan B 11cc2d41de81
task-resume is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 1,254 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.
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.
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…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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…
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
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…