opencode-dockerized: Skill for OpenCode

.opencode/config/skills/kanban-poller/SKILL.md

kanban-poller is a skill for OpenCode from mazumba/opencode-dockerized. It costs 57 tokens per session (7,534 once invoked), scanned A, original, MIT.

A workflow for operating and troubleshooting a Linear kanban poller. A kanban board is a list of work items moving through stages; this poller checks the board on a schedule and can trigger investigation, review, or fix actions.

In plain words
What is it for?
Use it to run or dry-run the poller, read its logs, explain why a ticket moved or did not move, or change its code and tests.
Why use it?
It provides explicit rules for how tickets are labelled, investigated, reviewed, and advanced, making automated board behaviour easier to inspect and debug.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions subagents; mentions OpenCode.

This is mazumba/opencode-dockerized's own configuration. It tells OpenCode how to work on opencode-dockerized itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything opencode-dockerized configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mazumba/opencode-dockerized. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mazumba/opencode-dockerized/main/.opencode/config/skills/kanban-poller/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mazumba/opencode-dockerized

Made for: OpenCode.

Wrote 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.

agentmods badge for kanban-poller

README.md
[![agentmods](https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/kanban-poller/github.svg)](https://agentmods.dev/skills/mazumba/opencode-dockerized/kanban-poller)
Your own site
<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/kanban-poller"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/kanban-poller/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.

agentmods 80×15 button for kanban-poller

Your own site · 80×15
<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/kanban-poller"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/kanban-poller.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.07534
Opus 5.5 $0.00023 $0.03014
Sonnet 5.5 $0.00011 $0.01507
Haiku 4.5 $0.00006 $0.00753

Measured 11d ago against content hash c310cacdd669, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kanban-poller 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 11d 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.

.opencode/config/skills/kanban-poller/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kanban poller

Code: docker/plugins/kanban/poller/. Tests: docker/plugins/kanban/tests/. Commands it runs: docker/plugins/kanban/kanban.commands/.

Who writes what

  1. The poller makes every Linear write (state, labels, comments, reactions), all through the --dry-run guard. Agents (ticket-worker|reviewer|investigator) have linear_* denied. Agents write only code and the PR (worker), the GitHub review (reviewer), and the report file (investigator).
  2. Before each work/fix/review/investigate run, and before the ticket is claimed or moved, the poller writes <path>/.slim/worktrees/.tickets/<ID>.json (atomic; passed as ctx.ticketFile; deleted when the job ends, also on failure; dry-run logs only). The snapshot state is the state at write time, so a work run sees the pre-move state. Content: title, description, state, labels, project name, url, attachments, all comments oldest to newest (id, parentId, author, isPoller, createdAt, body), state history. Cleanup works per ticket worktree and never touches .tickets.
  3. Every run ends with one last line KANBAN-RESULT: <json>. The poller takes the LAST such line (tolerating surrounding backticks, bold, or quote markers) and rejects unknown fields or values:
    1. Worker: {"outcome":"review","pr":<n>} or {"outcome":"needs-human","step","reason"}. review is accepted only if gh finds an OPEN PR on the branch with that number; then Agent review. Else Needs human.
    2. Reviewer: {"outcome":"approve"} → Ready for merge; {"outcome":"changes","summary"} → comment Agent review: changes requested (round n/2) — <PR> + one-line summary (prefixed Review: if it starts with CI failed or merge conflicts), label, In Progress, or Needs human ("review limit reached") at round ≥ 2; needs-human → Needs human with Agent review: needs human — <step>: <reason>.
    3. Investigator: {"outcome":"done"} plus the report in <path>/.slim/worktrees/.tickets/<ID>.investigation.md; the poller posts Agent investigation:\n\n<report> (cut at 60k characters with a note) as a reply to the request and reacts ✅. needs-human, a missing report, or a bad marker = ❌ + Agent investigation: failed — <reason>.
    4. Failed run (agent/server error, timeout, missing or invalid marker): one automatic retry, then Needs human ("agent result: marker missing|marker is not JSON|marker invalid", or the run failure).
    5. Work/fix: retry any failure IF nothing was pushed (remote branch head before the run = after a fetch; unknown counts as pushed). Review: retry only an agent/server error, not a timeout or missing marker.
    6. Retry = put the ticket back to its start lane (work: Ready for agent; fix: stays In Progress + agent:changes-requested; review: stays Agent review), THEN comment Agent: retrying (<lane>) — <reason>. That comment is the persisted budget (max 1 per lane entry), counted only from comments authored by the poller (user.id = API user) at or after the entry (work: last Ready for agent; review: last Agent review; fix: newest poller changes requested comment). The comparison is inclusive, so equal timestamps cannot grant another retry; a hard cap of 3 retry comments per lane per ticket ends loops whatever the timestamps. Log run.retry.
    7. A claim 👀 ends with its job (job finally, every outcome, released even if removing the ticket files fails; a reaction that is already gone is ignored); staleClaims ignores tickets labelled agent:changes-requested. Claims are written first (claimIssue: add the new reaction, then delete older ones), then the move/relabel.
    8. Session that could not be aborted (abort failed AND status still busy after 2 min): Needs human ("session could not be aborted"), never a retry or requeue.
    9. Poller stop (aborted run): same put-back, no comment, no budget used, log run.requeued; so a restart resumes the work. Investigations are not requeued (❌ poller stopped).
  4. Marker extraction (parseResult in select.ts) is separate from the transport (runner.ts gives the stdout tail). opencode run prints the final reply text to stdout; if the format ever wraps or decorates the line, fix only the line pattern.

Read the full file on GitHub · 175 lines

Changes

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.

  1. 11d ago Changed · +73 lines c310cacdd669
  2. 13d ago First seen · 102 lines · 57 tokens per session scan A aa81d8a23287

Subscribe to this mod's changes

kanban-poller is a skill published in the GitHub repository mazumba/opencode-dockerized (6 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 7,534 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 2026-10-13.

Related

Other skills, from other repositories

bug-triage

Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.

Donchitos/Claude-Code-Game-Studios · 30 tokens

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

triage-issue-reports

Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.

backnotprop/pstack · 46 tokens

triage-issue

Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…

atlassian/atlassian-mcp-server · 116 tokens

browse-flows

Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.

microsoft/power-platform-skills · 31 tokens

operating-cadence

Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…

cbrock84/headcount · 95 tokens