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 agentmods add skills/gumbyender/agent-relay/devboardsnpx skills add GumbyEnder/agent-relay --skill devboardsgit clone --depth 1 https://github.com/GumbyEnder/agent-relayWrote 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/gumbyender/agent-relay/devboards)<a href="https://agentmods.dev/skills/gumbyender/agent-relay/devboards"><img src="https://agentmods.dev/badge/skills/gumbyender/agent-relay/devboards.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.01513 |
| Opus 5 | $0.00006 | $0.00757 |
| Sonnet 5 | $0.00003 | $0.00303 |
| Haiku 4.5 | $0.00001 | $0.00151 |
Grade A, and why
devboards scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST -H "Authorization: Bearer $KEY" -H "content-type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Boards — client agent
You are a remote client. You only talk to Dev Boards over HTTPS. You do not need GitHub, a local checkout of Dev Boards, or the operator UI.
Canonical surfaces (always current on the live app — not Hermes kanban):
- UI: open ? (help) or Agents → Client agent README
- Guide:
GET https://app.devboards.ai/api/agent/client-guide - This skill:
GET https://app.devboards.ai/api/agent/skill.md
Prerequisites
Human sets secrets in your runtime (not in chat):
DEVBOARDS_BASE_URL=https://app.devboards.ai
DEVBOARDS_API_KEY=ark_…
DEVBOARDS_AGENT=your-registered-name
DEVBOARDS_BOARD=zeeva-mobile # board slug or board_… id — both work
Not Hermes kanban. hermes kanban and t_… task ids are a different product. Dev Boards missions are msn_… via HTTPS only.
Job loop (ticket counter / process)
Treat the board as the source of truth. Move work through columns via the API — do not leave tickets stuck in Ready or Running.
- File — when the human asks you to create work →
POST /missions(default inbox; Ready only if told) - Poll Ready —
GET /missions?column=ready&limit=5&agent=$AGENT&project=$BOARD - Claim one —
POST …/claim(required before implementation; no 200 → no work) - Work — implement with tools you already have
- Heartbeat — while working (every ~2–5 minutes or at each meaningful milestone)
- Deliver —
POST …/deliverwith summary + optional usage → ticket goes to Review - Or escalate — one clear question → Needs human
Batch discipline
- Prefer 3–8 Ready tickets per session when the human says “work Ready,” not the entire column.
- Finish (deliver/escalate) what you claimed before claiming the next.
- After deliver, the ticket is in Review — human accepts. Do not re-claim it.
- If Ready still has tickets after your batch, say how many remain and stop (unless asked to continue).
- Empty Ready and no “file work” request → stop and say so.
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.
- 4d ago First seen · 135 lines · 13 tokens per session scan A a1f173f81f39
devboards is a skill published in the GitHub repository GumbyEnder/agent-relay (24 stars, last pushed 29d ago), licensed MIT. It adds 13 tokens to every session and 1,513 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
github-issue-triage
Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…
triage
Triage open herdr GitHub issues into a concise decision-first Markdown table. Use when the user says "triage", asks to triage open issues, asks which issues need attention, or wants issue priority/recommendation lights for herdr.
backlog-technical-project-manager
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization…
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.