rosetta: Skill for Claude Code

.github/skills/promote-idea/SKILL.md

promote-idea is a skill for Claude Code from tikoci/rosetta. It costs 63 tokens per session (764 once invoked), scanned A, original, MIT.

A workflow for moving a shaped idea from the Inbox section of BACKLOG.md into either a GitHub issue or a structured briefing. It removes the original bullet after promotion.

In plain words
What is it for?
Use it to promote an Inbox item into a work issue when implementation is intended, or into a briefing when the idea needs further investigation.
Why use it?
It separates committed coding work from ideas that still need research or decision-making, so vague backlog notes do not become unclear tasks.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is tikoci/rosetta's own configuration. It tells Claude Code how to work on rosetta 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 rosetta configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tikoci/rosetta. 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/tikoci/rosetta/main/.github/skills/promote-idea/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tikoci/rosetta

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 promote-idea

README.md
[![agentmods](https://agentmods.dev/badge/skills/tikoci/rosetta/promote-idea.svg)](https://agentmods.dev/skills/tikoci/rosetta/promote-idea)
Your own site
<a href="https://agentmods.dev/skills/tikoci/rosetta/promote-idea"><img src="https://agentmods.dev/badge/skills/tikoci/rosetta/promote-idea.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 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 $0.00063 $0.00764
Opus 5 $0.00032 $0.00382
Sonnet 5 $0.00013 $0.00153
Haiku 4.5 $0.00006 $0.00076

Measured 7d ago against content hash 5b116aaeae56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

promote-idea 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 7d 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.

.github/skills/promote-idea/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promote Idea

Move a one-line Inbox bullet from BACKLOG.md to a real, structured location: a GitHub issue (codebase work) or a briefing (research/decision support).

When to use

  • An Inbox bullet has gained enough shape to either commit to or think through systematically.
  • After a discussion that resolves what an idea actually means.

When NOT to use

  • The bullet is still vague — leave it in Inbox until it has shape.
  • The bullet is one-shot ("merge this dependabot PR") — just do it; don't promote.
  • It's a wait-on-trigger item — move it to the BACKLOG.md Triggers section instead.

Procedure

  1. List Inbox bullets if no argument supplied. Read BACKLOG.md, find the ## Inbox section, present the bullets numbered.

  2. Pick the bullet. Match the substring argument, or ask the user which number.

  3. Decide: issue or briefing? Ask the user explicitly:

    • issue — "This is codebase work we intend to do." Discussion can continue on the issue; it only gets the agent-ready label once acceptance criteria are settled.
    • briefing — "I want to think this through, ground claims with code/data, possibly arrive at a decision. The conclusion might be 'no work needed' and that's fine."
    • delete — "This doesn't survive a re-read. Remove it."
    • trigger — "This is waiting on a specific external event." → move to the Triggers table instead.
  4. If issue: create it with gh issue create, using the work-item template's sections (context/grounding, acceptance sketch, V-* validation rows from VALIDATION.md, related briefings/issues). Only add the agent-ready label if the spec is genuinely settled — the default is an unlabeled discussion issue. If it belongs to an umbrella theme, mention the umbrella in the body and add it to the umbrella's child checklist.

  5. If briefing: find the next free B-NNNN ID across briefings/B-*.md, generate a kebab-case slug, ask for topic (one line) and an opening question for the body, and write briefings/B-NNNN-<slug>.md with status: open, last_revisited = today. Add it to the Briefings index in BACKLOG.md.

Read the full file on GitHub · 67 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. 7d ago First seen · 67 lines · 63 tokens per session scan A 5b116aaeae56

Subscribe to this mod's changes

promote-idea is a skill published in the GitHub repository tikoci/rosetta (43 stars, last pushed 21d ago), licensed MIT. It adds 63 tokens to every session and 764 once invoked, about $0.0003 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

daily-briefing

Start your day with a prioritized CRM briefing — works for any monday CRM setup: pipeline, contacts, accounts, leads, or no board at all. Use when someone says 'morning briefing', 'daily brief', 'what's on my plate today', 'catch me up on my deals', 'what needs attention', 'what needs my attention', 'anything urgent…

mondaycom/mcp · 106 tokens

meeting-to-deal

Turn meeting transcripts into deal updates — key points, commitments, and next steps posted to matching CRM deals automatically. Auto-creates contacts for new attendees. Use when someone says "log my meetings to deals", "update CRM from calls", "what did I commit to in meetings", "sync notetaker", "log this meeting"…

mondaycom/mcp · 107 tokens

workspace-builder

Build a CRM workspace from scratch — describe your business and get boards, columns, and pipeline stages created in monday. Use when someone says "set up my CRM", "build me a CRM", "create CRM boards for me", "I need a new sales pipeline", "help me get started in monday", "I don't know how to set up my pipeline", or…

mondaycom/mcp · 107 tokens

forecast

Build a forecast dashboard in monday — committed, best-case, and pipeline views by close month, rendered as real dashboard widgets. Use when someone says "build me a forecast", "show me Q2 pipeline", "Salesforce-style forecast", "forecast dashboard", "commit vs best-case", "what's our number this quarter", "how are we…

mondaycom/mcp · 102 tokens

log-activity

Log calls, meetings, notes, and other activities to CRM item timelines — structured records with attendees, outcomes, and follow-ups. Use when someone says "log my call with", "add a note to the deal", "what activities happened on", "record this meeting", "update my note on", "track a call with", "log a meeting with"…

mondaycom/mcp · 111 tokens

automate-crm

Set up, view, and manage automations on monday CRM boards using natural language — no block IDs or technical knowledge required. Use when someone says "set up an automation", "automate this", "when a deal is won notify me", "remind me when a date passes", "move deals automatically", "what automations do I have", "turn…

mondaycom/mcp · 99 tokens