rome: Skill for Claude Code

.claude/skills/todos-to-github-project/SKILL.md

todos-to-github-project is a skill for Claude Code from rome-os/rome. It costs 30 tokens per session (984 once invoked), scanned A, original, MIT.

A workflow for turning unfinished tasks from a conversation into tracked GitHub issues grouped in one GitHub Project, with links showing which tasks are blocked by others.

In plain words
What is it for?
Capturing deferred work, writing task-spec issues, ordering dependent tasks, and marking issues ready for an agent to handle.
Why use it?
It removes the need to manually reconstruct the task list and dependencies from chat. It also checks for existing issues so the tracker does not get duplicates.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is rome-os/rome's own configuration. It tells Claude Code how to work on rome 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 rome configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rome-os/rome. 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/rome-os/rome/main/.claude/skills/todos-to-github-project/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rome-os/rome

Made for: Claude Code.

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 todos-to-github-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/rome-os/rome/todos-to-github-project.svg)](https://agentmods.dev/skills/rome-os/rome/todos-to-github-project)
Your own site
<a href="https://agentmods.dev/skills/rome-os/rome/todos-to-github-project"><img src="https://agentmods.dev/badge/skills/rome-os/rome/todos-to-github-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 984 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 $0.00030 $0.00984
Opus 5 $0.00015 $0.00492
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 3d ago against content hash beb1d069794a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

todos-to-github-project 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 3d 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.

.claude/skills/todos-to-github-project/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Todos to GitHub project

Goal end-state: every remaining todo of the conversation is one task-spec issue, the issues sit in one GitHub project, every dependency is a blocked-by edge on GitHub, and each in-scope issue carries ready-for-agent.

The issue format — title, body sections, the ready-for-agent bar — is defined in docs/authoring/github-issues.md and docs/authoring/github-issues-task-spec.md. Prose in titles and bodies follows docs/authoring/WRITING.md. This skill covers what to file, in which order, and with which gh calls.

1. Harvest

  1. Collect every remaining todo from the conversation: open task-list items, deferred follow-ups, and work the user parked for later.
  2. Search the tracker for each todo with gh issue list --search "<keywords>". If an existing issue already tracks it, drop the todo from the set.
  3. Write one sentence per todo stating the outcome its issue must deliver. If the sentence only makes sense with the conversation open, ask the user what the todo means.

2. Draft

  1. Name the project after the outcome the set delivers, not after the conversation.
  2. Split the todos into in-scope and out-of-scope. An out-of-scope todo files under its issue type with the type label, stays out of the project, and never carries ready-for-agent.
  3. Draft each in-scope issue as a task spec in the github-issues-task-spec.md format, title included.
  4. Wire the dependencies. Issue X is blocked by issue Y when X cannot start before Y merges. Record each edge as a Blocked by line in X's body.
  5. Check the edge graph for cycles. A cycle is a decomposition error — re-split the todos until the graph is acyclic.
  6. Apply the label bar from github-issues-task-spec.md: every in-scope issue gets task, and an issue implementable from its body alone also gets ready-for-agent. An issue still waiting on a user decision files without ready-for-agent.

Read the full file on GitHub · 53 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. 3d ago Changed beb1d069794a
  2. 7d ago First seen · 53 lines · 30 tokens per session scan A 59b31c724084

Subscribe to this mod's changes

todos-to-github-project is a skill published in the GitHub repository rome-os/rome (478 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 984 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

pm-assistant

Product operations assistant strategy contract. PM short answers and deep analysis should be evidence-grounded and should separate facts from hypotheses. Model calls, hooks, queueing, cancellation, notifications, and staged task execution stay in Rust.

programming-pupil/aos · 0 tokens

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…

googleapis/mcp-toolbox · 159 tokens

meta-meeting-to-workflow

Use this meta-skill instead of answering directly when the user has meeting notes, transcripts, recordings, or rough discussion notes and wants them converted into decisions, owners, follow-ups, tasks, issues, or shareable minutes through multi-skill orchestration.

opensquilla/opensquilla · 58 tokens

meta-issue-to-pr-autopilot

Triages an issue, delegates the fix to sub-agent, drafts a PR description with summarize, and opens the PR via gh. Best used on small, well-scoped issues with clear acceptance criteria.

opensquilla/opensquilla · 117 tokens

meta-github-pr-watch-digest

Inspect the user's open GitHub PRs / failing CI / new issues via gh, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.

opensquilla/opensquilla · 48 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens