forge

A configuration approach that routes GitHub operations through external commands instead of calling the GitHub command-line tool directly.

In plain words
What is it for?
Use it to configure commands for viewing and listing issues, checking or managing pull requests, finding recent activity, identifying the current user, and running batched GraphQL queries.
Why use it?
It lets a project replace or customize how it reads issues, searches and merges pull requests, posts comments, and retrieves activity data.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/cluesmith/codev/forge
Any agent
npx skills add cluesmith/codev --skill forge
Clone the repo
git clone --depth 1 https://github.com/cluesmith/codev

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 695 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00695
Opus 5 $0.00000 $0.00347
Sonnet 5 $0.00000 $0.00139
Haiku 4.5 $0.00000 $0.00069

Measured yesterday against content hash 2865affd97d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge 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 yesterday.

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/forge/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge Concept Commands

Forge concept commands decouple codev from direct gh CLI calls. Each GitHub operation is routed through a configurable external command.

Concepts

Concept Env Vars Description
issue-view CODEV_ISSUE_ID Fetch issue details (JSON)
pr-list List open PRs (JSON array)
issue-list List issues (JSON array)
issue-comment CODEV_ISSUE_ID, CODEV_COMMENT_BODY Post a comment on an issue
pr-exists CODEV_BRANCH_NAME Check if a PR exists for a branch
recently-closed CODEV_SINCE_DATE (optional) List recently closed issues
recently-merged CODEV_SINCE_DATE (optional) List recently merged PRs
user-identity Get current user's handle (plain text)
team-activity CODEV_GRAPHQL_QUERY Run a batched GraphQL query
on-it-timestamps CODEV_ISSUE_NUMBERS, CODEV_GRAPHQL_QUERY, CODEV_REPO_OWNER, CODEV_REPO_NAME Get "on it" comment timestamps
pr-merge CODEV_PR_NUMBER Merge a PR
pr-search CODEV_SEARCH_QUERY Search PRs (JSON array)
pr-view CODEV_PR_NUMBER, CODEV_INCLUDE_COMMENTS (optional) View PR details (JSON or text)
pr-diff CODEV_PR_NUMBER, CODEV_DIFF_NAME_ONLY (optional) Get PR diff
auth-status Check forge authentication status

Configuration

In .codev/config.json:

{
  "forge": {
    "provider": "gitlab",
    "issue-comment": "my-custom-script $CODEV_ISSUE_ID"
  }
}

Resolution order

  1. Manual concept override in forge section
  2. Provider preset (if provider is set)
  3. Default (GitHub via gh CLI)

Providers

Built-in presets: github (default), gitlab (via glab), gitea (via tea).

Note: Non-GitHub presets are best-effort. Output schemas may differ from GitHub's JSON contracts. Non-conforming JSON returns null — consumers handle this gracefully. Override individual concepts if a preset doesn't match your CLI version.

Read the full file on GitHub · 69 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. yesterday First seen · 69 lines · 0 tokens per session scan A 2865affd97d5

Subscribe to this mod's changes

forge is a skill published in the GitHub repository cluesmith/codev (286 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 695 tokens. 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