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 Ani-HQ/session-warden --skill long-task-progressgit clone --depth 1 https://github.com/Ani-HQ/session-wardenWrote 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/ani-hq/session-warden/long-task-progress)<a href="https://agentmods.dev/skills/ani-hq/session-warden/long-task-progress"><img src="https://agentmods.dev/badge/skills/ani-hq/session-warden/long-task-progress/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/ani-hq/session-warden/long-task-progress"><img src="https://agentmods.dev/badge/skills/ani-hq/session-warden/long-task-progress.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 | $0.00044 | $0.00437 |
| Opus 5.5 | $0.00018 | $0.00175 |
| Sonnet 5.5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
long-task-progress scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Long-task progress card
Stay in this parent turn. Do not spawn Agent/Task children and exit.
Post one card. Edit that card. Never send a new "running…" message each tick.
# first tick
~/session-warden/bin/progress-card.sh start \
--agent "$AGENT" \
--channel "$SESSION_KEY" \
--title "short task name" \
--done 0 --total N \
--now "what you are doing" \
--sheet-url "$SHEET_URL"
# every 5 items, or when blocked, or when finished
~/session-warden/bin/progress-card.sh update \
--agent "$AGENT" \
--channel "$SESSION_KEY" \
--done K --total N \
--now "current item"
~/session-warden/bin/progress-card.sh done \
--agent "$AGENT" \
--channel "$SESSION_KEY" \
--done N --total N \
--now "finished"
$SESSION_KEY is the OpenClaw session key (example: agent:dash:discord:channel:123). Discord is inferred from that key. Set --telegram-target or WARDEN_PROGRESS_TELEGRAM_TARGET to fan out.
The helper throttles: at most one edit per 45s, or every 5 items, whichever comes first. start, done, and blocked always send.
Live cards include Stop and Steer. Clicks are handled by progress-card-actions (not a new message). Stop aborts the current run. Steer asks for a correction; the next message injects it. done drops those buttons.
The results sheet is the work artifact. The card is the live indicator. Do not use a sheet as the "still going?" UI.
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 Changed · +2 lines 44a18b25ba01
- 12d ago First seen · 41 lines · 44 tokens per session scan A 26024718a5ad
long-task-progress is a skill published in the GitHub repository Ani-HQ/session-warden (5 stars, last pushed 11d ago), licensed MIT. It adds 44 tokens to every session and 437 once invoked, about $0.0002 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 2026-09-17.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
welcome
Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.
add-teams
Add Microsoft Teams channel integration via Chat SDK.
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
daily-standup-journal
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.
scheduling-tasks
Advanced scheduling through the letta cron CLI for other conversations, computers, run history, and schedule replacement. Use Wake for ordinary create/list/cancel operations in the current conversation.