codev: Skill for Claude Code

.claude/skills/forge/SKILL.md

forge is a skill for Claude Code from cluesmith/codev. It costs 0 tokens per session (962 once invoked), scanned A, original, Apache-2.0.

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 Code

Written for Claude Code: installed under .claude/.

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

Reuse

Borrowing it

Nothing to install: this file belongs to cluesmith/codev. 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/cluesmith/codev/main/.claude/skills/forge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cluesmith/codev

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 forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/cluesmith/codev/forge/github.svg)](https://agentmods.dev/skills/cluesmith/codev/forge)
Your own site
<a href="https://agentmods.dev/skills/cluesmith/codev/forge"><img src="https://agentmods.dev/badge/skills/cluesmith/codev/forge/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 forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/cluesmith/codev/forge"><img src="https://agentmods.dev/badge/skills/cluesmith/codev/forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.00962
Opus 5.5 $0.00000 $0.00385
Sonnet 5.5 $0.00000 $0.00192
Haiku 4.5 $0.00000 $0.00096

Measured 17d ago against content hash 6e17dc0801f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 17d 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/forge/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 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-create CODEV_PR_TITLE, CODEV_PR_BODY, CODEV_PR_BASE (optional), CODEV_PR_HEAD (optional), CODEV_PR_REPO (optional), CODEV_PR_DRAFT (optional) Open a PR; prints {"number", "url"}
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), linear (Linear API), jira (Jira Cloud via acli). linear and jira are hybrid: they serve the issue concepts only, and every PR concept falls through to the gh default. Jira takes jira-site and jira-project keys; issue ids are work item keys (ENG-123).

Read the full file on GitHub · 72 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. 17d ago Changed 6e17dc0801f0
  2. 2mo ago Changed · +3 lines 033df1b221ad
  3. 2mo ago 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 (297 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 962 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

forge compared with skills from other repositories

forge next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
forgecluesmith/codevSkill297yesterdayApache-2.0A0Claude Code
moai-workflow-worktreemodu-ai/moai-adkSkill1.3ktodayApache-2.0A41Claude Code
moai-ref-git-workflowmodu-ai/moai-adkSkill1.3ktodayApache-2.0A58Claude Code
verifymodu-ai/moai-adkSkill1.3ktodayApache-2.0A60Claude Code
moai-syncmodu-ai/moai-adkSkill1.3ktodayApache-2.0A16Claude Code
ase-repo-reviewrse/aseSkill63todayApache-2.0A111Claude Code
release-checkPromptPartner/agentsmithSkill154yesterdayMITA43Claude Code