A shared guide for skills that manage GitHub Projects, GitHub's task boards for planning work. It defines setup files, startup checks, cached data, work sessions, and error handling.

Use it as a reference when building or maintaining skills that read GitHub Projects, track issue sessions, or need shared configuration and recovery rules.

It gives related skills the same rules for reading project data and handling missing or outdated information. This avoids repeating setup logic and inconsistent behavior.

ghpm-shared — Skill for Claude Code and Codex by jackchuka/ghpm

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add jackchuka/ghpm --skill ghpm-shared

Clone the repo

git clone --depth 1 https://github.com/jackchuka/ghpm

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jackchuka/ghpm/ghpm-shared/github.svg)](https://agentmods.dev/skills/jackchuka/ghpm/ghpm-shared)

Your own site

<a href="https://agentmods.dev/skills/jackchuka/ghpm/ghpm-shared"><img src="https://agentmods.dev/badge/skills/jackchuka/ghpm/ghpm-shared/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/jackchuka/ghpm/ghpm-shared"><img src="https://agentmods.dev/badge/skills/jackchuka/ghpm/ghpm-shared.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 861 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	$0.00025	$0.00861
Opus 5.5	$0.00010	$0.00344
Sonnet 5.5	$0.00005	$0.00172
Haiku 4.5	$0.00003	$0.00086

Measured 1mo ago against content hash 236997627390, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ghpm-shared 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 1mo 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.

skills/ghpm-shared/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ghpm — Shared Reference

Prerequisites

gh CLI installed and authenticated
Token scopes: read:project, project
GitHub Projects v2 (not classic projects)

Config Files

All ghpm files live under .ghpm/:

File	Purpose
`.ghpm/config.json`	Project config (fields, views, repos)
`.ghpm/cache.json`	Cached project items
`.ghpm/sessions/<number>.json`	Active work session per issue

The entire .ghpm/ directory is gitignored (project-specific).

If .ghpm/config.json is missing, tell the user to run /ghpm-init first and stop.

Startup Sequence

Every skill that reads project data should follow this sequence:

Read .ghpm/config.json from the current directory. If missing, stop with init guidance (above).
Load cache following references/cache.md. If the cache is stale or missing, automatically re-fetch — no user prompt needed. If the re-fetch fails (network error, rate limit), fall back to the stale cache if available and note the age inline (e.g., "Using cached data from 2 hours ago").
Check for stale sessions: list .ghpm/sessions/*.json. For each session file, read started_at and compare to now. If a session is older than 24 hours, prompt the user:
```
Found stale session for #<num> "<title>" (started <N> days ago).
Wrap up and post journal, or discard?
```
- Wrap up: follow the wrap-up sequence from ghpm-work (gather git context, post journal, clear session).
- Discard: delete the session file silently.
- If the user declines both, leave it and continue — don't block the current skill.

Error Handling

Auth expired (gh auth status fails): tell the user to run gh auth login and stop.
Rate limited (HTTP 403 with rate limit message): tell the user to wait and retry later.
Network error: if cache exists (even stale), offer to use stale cache as fallback.
Permission denied (HTTP 403/404 on project): tell the user to check token scopes (read:project, project).

Read the full file on GitHub · 74 lines

Files

What ships with it

6 files 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.

1mo ago First seen · 74 lines · 25 tokens per session scan A 236997627390

Subscribe to this mod's changes

ghpm-shared is a skill published in the GitHub repository jackchuka/ghpm (20 stars, last pushed 10d ago), licensed MIT. It adds 25 tokens to every session and 861 once invoked, about $0.0001 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 2026-08-30.

Project management claude github skills

git-issue-triage

Groom an open GitHub backlog with gh - one read-only sweep, every open issue bucketed into exactly one category (unlabeled, unprioritized, stale, likely duplicate, closeable, blocked, healthy), a per-issue report, per-category confirmation, then batched label / state / comment edits. Use when the user says "triage…

pivoshenko/pivoshenko.ai · 204 tokens

git-issue-create

Open one standalone GitHub issue with gh - duplicate-checked first, conventional title, repo-template-aware body, auto-resolved labels. Use for every issue-filing request however casual: "open an issue", "file a bug", "make a ticket", "/git-issue-create", "track this", "note this down", "we should fix X later", or…

pivoshenko/pivoshenko.ai · 157 tokens

git-issue-start

Take a GitHub issue from open to a checked-out branch - assign it to you, mark it in progress if the repo has such a label, derive a conventional branch name from its type: label, branch off the detected base. Use for "start issue 42", "work on #42", "/git-issue-start 42", "let's do 42", "pick up that issue", "take…

pivoshenko/pivoshenko.ai · 174 tokens

ghpm-shared