What is trello-handoff?

Instructions for moving the current Trello card through the Symphony for Trello workflow. They cover starting work, handing it to a person for review, recording blockers, and completing a merge.

Use them when picking up a card, changing its workflow list, recording a handoff or blocker, or marking work complete.

They make card status changes consistent and keep active lists from containing blocked or finished work.

How martin-francois/symphony-trello configures Codex

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/trello-handoff/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/martin-francois/symphony-trello/trello-handoff/github.svg)](https://agentmods.dev/skills/martin-francois/symphony-trello/trello-handoff)

Your own site

<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/trello-handoff"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/trello-handoff/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/martin-francois/symphony-trello/trello-handoff"><img src="https://agentmods.dev/badge/skills/martin-francois/symphony-trello/trello-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,643 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.03643
Opus 5.5	$0.00024	$0.01457
Sonnet 5.5	$0.00012	$0.00729
Haiku 4.5	$0.00006	$0.00364

Measured 6d ago against content hash 129d0d529a37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trello-handoff 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 6d 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/trello-handoff/SKILL.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trello Handoff

Goals

Move only the current card through configured board lists.
Leave clear Trello comments for humans.
Keep active lists free of blocked or completed work.
Use the workpad for detailed state and a short comment for the visible handoff.

Current-Card Tools

Use these scoped tools when they are advertised:

trello_move_current_card
trello_add_comment
trello_upsert_workpad
trello_update_blocker_recheck_status

The move tool uses Trello's term list_name for a board list name.

Every comment these tools write ends with a Written by Symphony footer. Do not type the footer yourself; Symphony adds it once and replaces a copied one. The footer only tells board users who wrote the comment. It does not turn a comment into a workpad or managed status, and a comment written by a person stays ordinary even when it repeats similar words.

Out-Of-Scope Follow-Ups

Classify actionable findings from implementation, review, CI inspection, tests, and command runs. This includes pre-existing bugs, errors, warnings, flaky tests, and environment-specific failures. Problems introduced or worsened by this change MUST be addressed within the current card. Creating a follow-up does not satisfy that obligation. If this change worsens a pre-existing problem, fix the regression here and track the remaining pre-existing problem separately.

Before creating a follow-up for a discovered problem, establish that it already exists on the actual target branch of the change, such as the PR's base branch, not an assumed default branch. Record the repository, branch, exact commit, and baseline evidence. Use an isolated checkout or existing CI results for that revision. Compare relevant tool versions and environment conditions. If baseline evidence is unavailable, keep the finding and verification gap in the workpad; do not present it as a confirmed pre-existing problem or create its follow-up yet.

Search existing cards and issues before creating another. When the trello_create_follow_up_card tool is available, call it once per distinct out-of-scope item with a one-line title, a self-contained description, and acceptance criteria. Another agent MUST be able to address the card using only its description and the codebase, without the original session or machine. Include:

Read the full file on GitHub · 319 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.

6d ago Changed · +2 lines 129d0d529a37
9d ago Changed · +8 lines 18553865ba1a
10d ago Changed · +33 lines 62f34d711227
12d ago Changed · +58 lines · +20 tokens per session 152b646c4107
2mo ago First seen · 218 lines · 41 tokens per session scan A 263c14ebcaaa

Subscribe to this mod's changes

trello-handoff is a skill published in the GitHub repository martin-francois/symphony-trello (5 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 3,643 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.

Project management agent-orchestration agentic-ai agentic-coding agentic-workflow ai ai-agents

trello-handoff next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
trello-handoffmartin-francois/symphony-trello	Skill	5	today	Apache-2.0	A	61	Codex
assimilate-popular-workflowsa5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	110	Claude Code
mcp-app-verificationa5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	48	Claude Code
guardrails-ai-setupa5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	30	Claude Code
mcp-host-styling-integrationa5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	44	Claude Code
frontmatter-parsinga5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	40	Claude Code
rag-hybrid-searcha5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	28	Claude Code

symphony-trello: Skill for Codex