gh-cli-projects-tasks-conventions

gh-cli-projects-tasks-conventions is a skill for Claude Code, Codex from lossless-group/lossless-agent-skills. It costs 316 tokens per session (5,642 once invoked), scanned A, a copy of 043-planning-github-issues, MIT.

A set of conventions for using GitHub's command-line tool to manage issues and Projects tasks across a pseudomonorepo. A pseudomonorepo is a group of related repositories arranged and worked with like one larger codebase.

In plain words
What is it for?
Use it when creating, editing, or listing GitHub Project tasks, creating repository issues, or deciding which repository contains a local path.
Why use it?
It keeps task links, branches, and issue details consistent, which helps teams avoid creating work in the wrong repository or branch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/mpstaton/code/lossless-monorepo/ai-labs/context-v/explorations/X.md.

Good fit Use it when creating, editing, or listing GitHub Project tasks, creating repository issues, or deciding which repository contains a local path.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, 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 gh-cli-projects-tasks-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/gh-cli-projects-tasks-conventions/github.svg)](https://agentmods.dev/skills/lossless-group/lossless-agent-skills/gh-cli-projects-tasks-conventions)
Your own site
<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/gh-cli-projects-tasks-conventions"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/gh-cli-projects-tasks-conventions/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 gh-cli-projects-tasks-conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/gh-cli-projects-tasks-conventions"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/gh-cli-projects-tasks-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 316 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,642 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 86% copy Near-identical to another mod 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 $0.00316 $0.05642
Opus 5 $0.00158 $0.02821
Sonnet 5 $0.00063 $0.01128
Haiku 4.5 $0.00032 $0.00564

Measured 10d ago against content hash 743ae101924c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gh-cli-projects-tasks-conventions 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 10d 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.

Origin

This is a copy

86% identical to 043-planning-github-issues — 395 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

gh-cli-projects-tasks-conventions/SKILL.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gh CLI · Projects & Tasks Conventions

Premature on purpose — 2026-06-05. We don't yet have many preferences. The ones that exist are codified here so they don't drift in the meantime — listed in order of priority to adhere to, not in the order they were added: (1) compose with [[pseudomonorepos]] to figure out which repo a local path actually lives in; (2) every task body that points at a context-v/ file points at it via a clickable GitHub URL; (3) pin the branch explicitly when worktrees are in play, because HEAD answers per-worktree; (4) prefill the issue sidebar — assignee, label, type, milestone — by querying the available options and inferring best fit, asking the user only when nothing fits (Convention 6). As more conventions emerge (status field discipline, priority discipline, custom-field schemas, project-per-app vs project-per-engagement), they get added here.

When to use this skill

  • Creating, editing, or listing GitHub Project tasks via gh project — particularly item-create, item-add, item-edit.
  • Creating repo issues via gh issue create whose sidebar (assignee, labels, type, milestone) should arrive prefilled (Convention 6).
  • The user says "create a task," "add to the project," "draft a project item," "set up a project," "gh project," or any variant.
  • An agent is about to author a task body that references one or more context-v/ files anywhere in the pseudomonorepo tree.
  • Scripting bulk task creation from a spec, exploration, or plan that has sections / decisions / placeholders worth tracking.
  • Any of the above while git worktrees are in play — multiple checkouts of the same repo at different branch tiers change what HEAD resolves to, and therefore which branch ends up in the link (Convention 3b).

Compose with pseudomonorepos

This skill assumes [[pseudomonorepos]] is in context. The tree-walking discipline there is what makes the link-building behavior below correct: a context-v/ file at /Users/mpstaton/code/lossless-monorepo/ai-labs/context-v/explorations/X.md does not live in the lossless-monorepo repo on GitHub — it lives in the ai-labs repo, which is submoduled. The link convention below depends on resolving the right repo before building the URL.

Read the full file on GitHub · 379 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. 10d ago First seen · 379 lines · 316 tokens per session scan A 743ae101924c

Subscribe to this mod's changes

gh-cli-projects-tasks-conventions is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 17d ago), licensed MIT. It adds 316 tokens to every session and 5,642 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to 043-planning-github-issues, differing in 395 lines, and is treated as a copy.