symphony-trello: Skill for Codex

.codex/skills/github-issues-to-trello-cards/SKILL.md

github-issues-to-trello-cards is a skill for Codex from martin-francois/symphony-trello. It costs 79 tokens per session (1,236 once invoked), scanned A, original, Apache-2.0.

An automation skill that turns GitHub issues—tracked software tasks—into Trello cards, which are visual task-management items.

In plain words
What is it for?
Creating or synchronizing cards from selected GitHub issues, choosing the right Trello board, and reporting new, unchanged, or renamed cards.
Why use it?
It avoids manually copying issues and prevents duplicate cards while keeping card titles aligned with GitHub.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

This is martin-francois/symphony-trello's own configuration. It tells Codex how to work on symphony-trello 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 symphony-trello configures →

Reuse

Borrowing it

Nothing to install: this file belongs to martin-francois/symphony-trello. 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/martin-francois/symphony-trello/main/.codex/skills/github-issues-to-trello-cards/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/martin-francois/symphony-trello

Made for: Codex.

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 github-issues-to-trello-cards

README.md
[![agentmods](https://agentmods.dev/badge/skills/martin-francois/symphony-trello/github-issues-to-trello-cards/github.svg)](https://agentmods.dev/skills/martin-francois/symphony-trello/github-issues-to-trello-cards)
Your own site
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/github-issues-to-trello-cards"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/github-issues-to-trello-cards/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 github-issues-to-trello-cards

Your own site · 80×15
<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/github-issues-to-trello-cards"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/github-issues-to-trello-cards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,236 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 $0.00079 $0.01236
Opus 5 $0.00039 $0.00618
Sonnet 5 $0.00016 $0.00247
Haiku 4.5 $0.00008 $0.00124

Measured 11d ago against content hash 731c2a258709, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

github-issues-to-trello-cards 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.

.codex/skills/github-issues-to-trello-cards/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issues To Trello Cards

Goals

  • Create one Trello card per requested GitHub issue.
  • Use the GitHub issue title as the Trello card title.
  • Use exactly Implement <issue-url> as the description for newly created cards.
  • Avoid duplicate cards by checking the target board for an existing card whose description contains the canonical GitHub issue URL as a standalone URL token before creating anything.
  • For existing cards, update only the Trello title when it differs from the current GitHub issue title.
  • Report created cards, existing unchanged cards, and existing title-updated cards separately.

Workflow

  1. Resolve every requested issue through GitHub before touching Trello. Use canonical issue URLs and current titles from GitHub, not user-supplied title text. Deduplicate repeated issue inputs by canonical URL while preserving the user's order.
  2. If the user gave a Trello board selector, use that board.
  3. If no board selector was given, auto-select from configured workflows:
    • Inspect local workflow files such as WORKFLOW.md, WORKFLOW.*.md, and configured Symphony for Trello workflow paths.
    • Find workflows whose repository source matches the GitHub repository for the issue. Compare both repository.default_url and repository.default_path. For URLs, canonicalize common HTTPS and SSH GitHub clone URL forms before comparing. For local paths, resolve the path relative to the workflow file when needed, inspect the checkout's Git remotes, and canonicalize those remote URLs before comparing.
    • Use the workflow's configured Trello board only when exactly one board matches the relevant repository. If there is no match or more than one match, stop and ask the user for the board instead of guessing.
  4. If the issues span multiple GitHub repositories and the user did not provide one board, group issues by repository and apply the same exact-one workflow board match per repository. Stop before Trello writes for any ambiguous group.
  5. Resolve the target list for new cards. Use the open Inbox list when it exists. If the board has no open Inbox list, stop and ask which list to use instead of creating cards in another list.
  6. Before creating cards, fetch all cards on the target board, including archived cards when the Trello API supports it. Match existing cards by the canonical GitHub issue URL in the card description only when the URL is delimited by the start or end of text, whitespace, or punctuation that cannot be part of a GitHub issue URL. Do not treat prefix-sharing URLs as matches, such as matching /issues/1 inside /issues/12, and do not rely on Trello card title alone.
  7. For each issue:
    • If no matching card exists, create a new card in the resolved target list with the GitHub issue title and Implement <issue-url> description.
    • If one or more matching cards exist and every matching card title already equals the GitHub issue title, leave Trello unchanged and report it as existing unchanged.
    • If one or more matching cards exist and any matching card title differs from the GitHub issue title, update the differing Trello titles and report the issue as existing title-updated.
    • If multiple matching cards exist, do not create another card. Report the duplicate Trello card URLs so the user can decide whether to merge or archive extras.
  8. Do not edit GitHub issue bodies, labels, assignees, or milestones while creating Trello cards. If the work also requires creating or editing GitHub issues, use issue-sweep or read ../../../docs/agents/github-issue-triage.md first and apply the canonical issue policy there.

Read the full file on GitHub · 110 lines

Files

What ships with it

1 file beside 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.

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 First seen · 110 lines · 79 tokens per session scan A 731c2a258709

Subscribe to this mod's changes

github-issues-to-trello-cards is a skill published in the GitHub repository martin-francois/symphony-trello (2 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 1,236 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

gsd-tools

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

a5c-ai/babysitter · 62 tokens

moai-workflow-spec

SPEC workflow orchestration with EARS format requirements, acceptance criteria, and Plan-Run-Sync integration for MoAI-ADK development. Use when creating SPEC documents or defining acceptance criteria.

modu-ai/moai-adk · 44 tokens

moai-workflow-worktree

Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.

modu-ai/moai-adk · 41 tokens

babysit-babysitter-issues

This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.

a5c-ai/babysitter · 69 tokens

moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…

modu-ai/moai-adk · 76 tokens

cog-meeting-processing

Process meeting recordings and transcripts into decisions, action items, and team dynamics.

a5c-ai/babysitter · 20 tokens