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 epicsagas/plugins --skill kanban-dev-lanegit clone --depth 1 https://github.com/epicsagas/pluginsWrote 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/epicsagas/plugins/kanban-dev-lane)<a href="https://agentmods.dev/skills/epicsagas/plugins/kanban-dev-lane"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/kanban-dev-lane/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/epicsagas/plugins/kanban-dev-lane"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/kanban-dev-lane.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 | $0.00058 | $0.01300 |
| Opus 5.5 | $0.00023 | $0.00520 |
| Sonnet 5.5 | $0.00012 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
kanban-dev-lane 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kanban Dev Lane (Multi-Engine Autonomous Implementation Lane)
Overview
The kanban-dev-lane plugin enables Hermes Kanban workers (specifically dev-lead and devops-lead) to delegate bounded implementation work into an isolated git worktree with an automatic, resilient 3-tier failover chain:
[Hermes Worker (dev-lead)]
│
▼
┌──────────────────────────────────────────────────────────┐
│ Isolated Git Worktree: /tmp/<task_id>-dev-lane │
└──────────────────────────────────────────────────────────┘
│
┌─────┴─────────────────────────────────────────┐
▼ ▼
Tier 1: Claudy (Primary) [Success] ──► Hermes Reconcile & Verify
│ (Quota Exhaustion / 429 / Error)
▼
Tier 2: Codex (`codex exec ...` / `--yolo`) [Success] ──► Hermes Reconcile & Verify
│ (Quota Exhaustion / Error)
▼
Tier 3: AGYD (`agy --dangerously-skip-perms`) [Success] ──► Hermes Reconcile & Verify
│ (All Engines Exhausted)
▼
Tier 4: Hermes Agent Direct Execution ────────────────────► Hermes Complete / Block
Hermes is always the task owner: it controls worktree lifecycle, diff inspection, regression testing, and final board completion. External CLIs serve as isolated input engines only.
When to Use
Use kanban-dev-lane when:
- The task is a coding, refactoring, documentation, or test implementation task (
DEV-*,OPS-*). - Acceptance criteria and scope constraints are clearly stated in the Kanban card.
- An isolated git worktree can be created without dirty checkout conflicts.
- Hermes can execute canonical verification commands after the engine finishes.
- At least one engine CLI (
claudy,codex,agy) is available onPATH.
Capability Check
command -v claudy && claudy --version
command -v codex && codex --version
command -v agy && agy --version
Worktree Isolation Pattern
TASK_ID="${HERMES_KANBAN_TASK:-t_manual}"
REPO="/path/to/repo"
BASE="$(git -C "$REPO" rev-parse --abbrev-ref HEAD)"
SAFE_TASK="$(printf '%s' "$TASK_ID" | tr -cd '[:alnum:]_-')"
BRANCH="lane/${SAFE_TASK}/$(date -u +%Y%m%d%H%M%S)"
WORKTREE="/tmp/${SAFE_TASK}-dev-lane"
git -C "$REPO" fetch --all --prune
git -C "$REPO" worktree add -b "$BRANCH" "$WORKTREE" "$BASE"
What ships with it
4 files beside kanban-dev-lane.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.
- 1mo ago First seen · 149 lines · 58 tokens per session scan A ea76a273ab68
kanban-dev-lane is a skill published in the GitHub repository epicsagas/plugins (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,300 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 2026-08-31.
Other skills, from other repositories
sdlc
Run an artifact-driven software lifecycle where each stage commits a markdown artifact that triggers the next - intent.md, spec.md, plan.md, verified diff, reviewed PR, monitored production. Use when the user asks to capture an idea as intent, write a spec, plan before implementing, set up a verification loop, define…
morning-brief
Operator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, loop-lane telemetry freshness, and per CI lane the week's failures by class, limit stops, restarts and turn headroom, and model usage per activity and…
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
survey
A project-discovery workflow that creates `.claude/context.md`, a shared file describing the project's purpose, design, constraints, and measures of success.
glue-audit
Use when the user wants to systematically identify, categorize, and quantify "glue work" on themselves or their team. Trigger phrases include "what glue work am I doing", "audit my glue work", "what non-promotable work is our team doing", "catalog our glue tasks", "how much time do we spend on glue", "map our glue…
manage-glue-workers
Use when managing engineers who gravitate toward glue work (onboarding, documentation, unblocking) and need burnout protection, visibility, and career development that doesn't force them off the IC track. Trigger phrases include "my report does too much glue", "how do I protect my glue person", "glue worker…