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 joelbrilliant/agentic-delivery-skills --skill visible-agent-workgit clone --depth 1 https://github.com/joelbrilliant/agentic-delivery-skillsWrote 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/joelbrilliant/agentic-delivery-skills/visible-agent-work)<a href="https://agentmods.dev/skills/joelbrilliant/agentic-delivery-skills/visible-agent-work"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/visible-agent-work/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/joelbrilliant/agentic-delivery-skills/visible-agent-work"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/visible-agent-work.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 | $0.00054 | $0.00661 |
| Opus 5 | $0.00027 | $0.00331 |
| Sonnet 5 | $0.00011 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
visible-agent-work 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 12d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visible Agent Work
Overview
Use this skill when agents delegate work or run background tasks and the user needs to see what is happening.
Invisible work creates distrust. If a child agent is working, the parent surface should show the task, run ID, status, and completion evidence.
When to Use
- Parent agents dispatch builders, reviewers, or research workers.
- A UI shows a right rail, task list, activity card, or progress stream.
- Users ask whether an agent is actually working.
- Background processes are used as proof.
- A platform supports run IDs, task records, logs, or streamed events.
Core Rules
- Visible ID or it did not happen. Prefer task IDs, run IDs, PRs, commits, or transcript handles over hidden process IDs.
- Task-local only. Show work connected to the selected parent task. Do not fall back to global agent activity.
- Stream truth, not theatre. Do not fake token streaming with final ledger updates.
- Keep completed work visible briefly. If active rows disappear immediately on completion, users think the work vanished.
- Parent chat should mirror child work. A side rail alone is not enough for important child-agent progress.
Required Fields
Each visible child work item should have:
- child run ID or task ID;
- agent name and role;
- status: queued, invoking, streaming, completed, failed, interrupted, stalled;
- compact task title;
- request preview;
- response or output preview when safe;
- link to full transcript, artefact, PR, or log;
- timestamps.
Parent-Child Association
Associate child work with the parent task using explicit references:
- parent thread mentions child
run-...; - parent task record lists child IDs;
- dispatch ledger links parent ID to child ID;
- PR/check metadata links review/fix runs.
Never infer association from same agent name or recent global activity alone.
Streaming Contract
If streaming is supported, use durable run IDs:
{
"event": "stream_delta",
"run_id": "run-...",
"agent": "reviewer",
"role": "reviewer",
"delta": "token text"
}
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.
- 12d ago First seen · 90 lines · 54 tokens per session scan A 0690ef401c5d
visible-agent-work is a skill published in the GitHub repository joelbrilliant/agentic-delivery-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 661 once invoked, about $0.0003 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
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…
hsb-ip-packetizer
Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
deepstream-run-mv3dt
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custom synchronized MP4 datasets, import camera calibration, delegate missing calibration to AutoMagicCalib, inspect OSD or…