forge-code

A coding workflow for turning approved Forge issues into code changes. It creates a branch, follows an existing plan, builds and tests the project, reviews the result, then commits and pushes the changes.

In plain words
What is it for?
Use it to implement one or more approved issues, validate the result locally, and optionally deploy a preview when the project has deployment setup.
Why use it?
It keeps implementation work tied to a tracked issue and checks the changes before they are shared. An existing plan reduces repeated codebase exploration.

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/sidcorp-co/forge/forge-code
Any agent
npx skills add SidCorp-co/forge --skill forge-code
Clone the repo
git clone --depth 1 https://github.com/SidCorp-co/forge

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00082 $0.03397
Opus 5 $0.00041 $0.01699
Sonnet 5 $0.00016 $0.00679
Haiku 4.5 $0.00008 $0.00340

Measured yesterday against content hash b0d92d2aef16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-code scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

7. Test API (if plan has API Test Plan) — curl affected endpoints, verify responses. Skip for frontend-only.
packages/core/skills/forge-code/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge Code

The coding step in the issue pipeline: approved → developed. Implements code, validates it locally (build + test), then pushes. An independent review step follows.

When a plan exists (from forge-plan), this skill should be fast and focused — the plan already identified the files, the approach, and the patterns. Don't re-explore. Follow the plan, edit the files, test, commit.

Usage

/forge-code <documentId>
/forge-code <documentId1> <documentId2>

Tools

forge_issues, forge_comments, forge_coolify_deploy, plus codebase tools (Read, Edit, Write, Glob, Grep, Bash).

Deploy Mode Detection (do this FIRST, once per run)

Before following the workflow below, call forge_config → get and forge_coolify_deploy → list. Decide deployMode for this project:

  • local-onlypreviewDeploy is null/missing OR has no stagingUrl, AND forge_coolify_deploy → list returns empty. Project builds only locally; no staging, no production deploy infrastructure.
  • deploy — Coolify resources are configured OR previewDeploy.stagingUrl is set. Deploy mode has two topology sub-modes — read baseBranch and productionBranch from that same forge_config → get call (never assume, never hardcode which one is "safe to merge to"):
    • deploy · distinct-branch (baseBranch !== productionBranch) — baseBranch is a non-production integration branch; merging there is safe for every complexity because it only reaches a pre-prod environment.
    • deploy · same-branch (baseBranch === productionBranch) — there is no separate integration branch; merging to baseBranch IS merging to production. Never merge or deploy here, for any complexity — push the ISS-* branch only and defer the merge + deploy to forge-release, which runs after independent review and QA have passed, not before.

The three sub-modes differ only in steps 11 and 13 (push + status). Everything else (branch, build, test, review, commit, session context) is identical.

Read the full file on GitHub · 159 lines

Files

What ships with it

2 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.

  1. yesterday First seen · 159 lines · 82 tokens per session scan A b0d92d2aef16

Subscribe to this mod's changes

forge-code is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 3,397 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ad-creative

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…

rondoflow/rondoflow · 142 tokens

ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…

rondoflow/rondoflow · 135 tokens

ab-testing

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test…

rondoflow/rondoflow · 165 tokens

adaptive-anti-bot-web-scraping

Adaptive web scraping framework with anti-bot bypass and spider crawling.

rondoflow/rondoflow · 23 tokens

access-gevety-health-biomarker-data

Access your Gevety health data - biomarkers, healthspan scores, biological age, supplements, activities, daily actions, 90-day health protocol, and upcoming tests.

rondoflow/rondoflow · 43 tokens

access-fireflies-meeting-transcripts-analytics

Access Fireflies.ai meeting transcripts, summaries, action items, and analytics via GraphQL API.

rondoflow/rondoflow · 28 tokens