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 S3YED/appie-kit --skill kanban-agent-workflowsgit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/kanban-agent-workflows)<a href="https://agentmods.dev/skills/s3yed/appie-kit/kanban-agent-workflows"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/kanban-agent-workflows/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/s3yed/appie-kit/kanban-agent-workflows"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/kanban-agent-workflows.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 | $0.00057 | $0.00524 |
| Opus 5 | $0.00028 | $0.00262 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
kanban-agent-workflows 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 9d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kanban Agent Workflows
Use this umbrella for Hermes Kanban work. The board is the durable boundary between orchestrators and workers; do not bypass it for multi-agent work that should survive a single session.
Orchestrator role
Use the board when work benefits from parallelism, specialist profiles, durable handoff, or isolation. Do not use it for a tiny single-turn task.
Orchestrator flow:
- Understand the user's goal and acceptance criteria.
- Sketch a dependency graph before creating cards.
- Create focused tasks with clear inputs, outputs, and verification requirements.
- Link dependencies so workers can start only when prerequisites are complete.
- Assign tasks to the right specialist profile.
- Complete the orchestrator task after the board is set up, then report routing decisions.
Anti-temptation rule: if you are acting as orchestrator, do not secretly implement worker tasks yourself just because you can.
Worker role
Worker flow:
- Read the assigned card and linked context.
- Work only inside the assigned workspace/tenant boundary.
- Send useful heartbeats for long tasks.
- Complete with a summary that includes files changed, verification run, and follow-up needs.
- Block instead of guessing when credentials, access, or upstream artifacts are missing.
Good block reasons are specific and answerable: missing env var, unavailable repo path, failing upstream task, ambiguous acceptance criterion.
Task design patterns
- Fan-out/fan-in: split independent implementation/research tasks, then create a synthesis/review task depending on all outputs.
- Reviewer lane: create a second task for review/verification before merge or delivery.
- Recovery lane: when a worker blocks, create a small unblocker task instead of rewriting the original task.
Pitfalls
- Do not claim cards by guessed IDs; capture returned IDs from create/list calls.
- Do not mix tenants/workspaces; isolation matters more than convenience.
- Do not leave long-running tasks silent; heartbeat with meaningful progress.
- Do not mark complete without verification evidence or an explicit blocker.
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.
- 9d ago First seen · 53 lines · 57 tokens per session scan A 5612425f0eac
kanban-agent-workflows is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 17d ago), licensed MIT. It adds 57 tokens to every session and 524 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 2026-09-03.
Other skills, from other repositories
event-planner
Event planning with timelines, budgets, vendor coordination, logistics checklists, and post-event evaluation. Use when organizing conferences, workshops, galas, or corporate events.
proposal-writer
Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service…
standup-summary
Tell Gemma what you did, what you're working on, and any blockers. Get a clean standup update.
lenny-podcast
Product management advisor drawing from 269+ Lenny's Podcast episodes and established PM frameworks. Searches transcripts for practitioner wisdom on strategy, growth, prioritization, user research, metrics, and product decisions. Triggers on: "what does Lenny say about", "ask lenny", "PM advice", "product strategy…
configure-pm-pilot
Interactive setup wizard for PM Pilot. Detects MCP tools, sets company name, creates memory template, validates installation.
teamboard
Shared team board: claim a work item before starting, hand it over, finish it. The claim is a git-ref lock, so two people cannot take the same item.