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 sonichi/sutando --skill task-progressgit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/task-progress)<a href="https://agentmods.dev/skills/sonichi/sutando/task-progress"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/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/sonichi/sutando/task-progress"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/task-progress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 131 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00000 | $0.03080 |
| Opus 5.5 | $0.00000 | $0.01232 |
| Sonnet 5.5 | $0.00000 | $0.00616 |
| Haiku 4.5 | $0.00000 | $0.00308 |
Grade A, and why
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 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-progress
Sends mid-task progress updates to the channel a task came from (Slack, Discord, Telegram, or an AG2 Space room).
Critical rule — if you notify, notify BEFORE any work begins
For tasks that need a progress update, call notify.py as the FIRST action after reading the task — before transcription, web searches, code reads, or any other tool call. The user's first signal that you received a long-running task must be the notification, not silence followed by a result minutes later.
Critical rule — progress only, never final answers
notify.py is only for short progress/status updates. Do not use it to send the
answer, findings, recommendations, completed list, PR summary, or any other final result.
Final task delivery must go through the authoritative task result file
(results/task-<id>.txt, or the channel-specific result path named in the task).
Keep notify bodies short: at most 280 characters and 4 non-empty lines. The script rejects longer messages so a final answer cannot accidentally be sent directly and then duplicated by the bridge when it delivers the result file.
If you already sent the final answer through another approved path, write [REPLIED]
to the task result file so the bridge archives the task without sending a duplicate.
Voice message tasks (most common failure case)
When a task contains a voice attachment ([File attached: ...]), notify BEFORE calling the
transcription script. Transcription takes 10–30 seconds — the user should not wait in silence.
Wrong order:
- Read task (sees voice attachment)
- Call transcribe.py ← 20s of silence
- Process transcript
- Return result ← user waited 60+ seconds with no signal
Correct order:
- Read task (sees voice attachment)
- Notify: "Got your voice message, give me a moment." ← user knows within seconds
- Call transcribe.py
- Process — if research needed, notify again before starting
- Return result
All other long-running tasks
Wrong order:
- Read task
- Do research (WebSearch, WebFetch, file reads, analysis...)
- ← user waits 2 min with no signal
- Notify "on it"
- Return result
What ships with it
3 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.
- 6d ago Changed · +9 lines 4c96df7a9508
- 9d ago Changed · +27 lines 26168f5cb648
- 16d ago Changed · +1 lines 753f5530310d
- 20d ago Changed · +52 lines a90c661a08c1
- 25d ago Changed · +18 lines 103e33e5f6d8
- 1mo ago First seen · 138 lines · 0 tokens per session scan A 00497d7fb2bf
task-progress is a skill published in the GitHub repository sonichi/sutando (397 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,080 tokens. 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 2026-08-30.
Other skills, from other repositories
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
stripe-link-wallet
Agent wallet on the Stripe Link CLI (link-cli). Connect the wallet, then buy, purchase and pay for things on the user's behalf via approved spend requests, one-time-use cards, and 402 / Machine Payment Protocol (MPP) payments.
media-processing
Ingest and process media files (video, audio, image).