forge
01Plugin Claude Code
Plugin marketplace listing 1 plugin: forge.
Plugin Claude Code
Plugin marketplace listing 1 plugin: forge.
Plugin Claude Code
An agent-engineering workflow skill set (fg-) for Claude Code. Includes fg-security, a codebase security audit (methodology vendored from cloudflare/security-audit-skill, MIT) whose artefacts stay outside the repo and whose severity-gated findings become fix-forward plans. A development loop that takes one task throug.
Agent Claude Code
A synchronization guide for Forge’s catalogue and manifest documents, which repeat facts such as skill lists, counts, and versions.
Agent Claude Code
A coding agent for building and maintaining deterministic script twins for Forge, a system that keeps subjective language-model decisions in written guidance and extracts repeatable surveys and state changes into scripts.
Agent Claude Code
An agent that writes Markdown instructions for skills used by the forge Claude Code plugin and marketplace. Its documents are the instructions that agents read and follow; there is no build or test system.
Skill Claude CodeCodex
Review the open GitHub issues of the current repo and triage them — classify, summarize, and score each one's fix-worthiness against the project's own docs — then print a ranked report so you can decide which to act on. Read-only: it fetches via the gh CLI and writes nothing (no files, no labels, no comments). It…
Instructions file
Project instructions for working on the Forge add-on, including its configuration file and marketplace setup. They also explain that the manifest must remain valid JSON because invalid data prevents installation.
Hook
Runs when a session starts on startup, resume, clear and compact, executing run-hook.cmd. From gyuha/forge.
Hook
Runs when the agent finishes a response, executing run-hook.cmd. From gyuha/forge.
Skill Claude CodeCodex
Optional adversarial review between fg-run and fg-learn — a reviewer assumes the result is WRONG and hunts for evidence across six lenses (failure points, hidden assumptions, misread requirements, security/perf/data-loss, unexpected misuse, weak decisions), fanning out as parallel subagents; fix-needed findings become…
Skill Claude CodeCodex
A decision queue for foggy work — outside the forge loop. Settles the destination with you, grills breadth-first to surface what must be decided, and keeps it in .forge/agenda.md (destination · decided · open questions · fog · out of scope), resolving one question at a time via fg-ask until the way is clear, then…
Skill Claude CodeCodex
Generates a project's domain agents — conversational grilling derives the recurring roles, then writes standard Claude Code subagent cards to .claude/agents/ .md (each description carrying a "when to use" so fg-run can dispatch a matching role as agentType). Cards load only at session start, so RESTART the session…
Skill Claude CodeCodex
Grilling session that stress-tests your plan against the project's domain model, terminology, and documented decisions, updating CONTEXT.md/ADRs inline. The forge loop's entry point (the plan-grilling stage), always conversational. Use to start or refine a task — "start a new task", "start with forge", "let's work on…
Skill Claude CodeCodex
Retires stale or superseded ADRs out of the active decision set — proposes candidates with rationale, and on your approval moves each to .forge/adr/retired/ (IDs never reused, nothing deleted). fg-ask stops reading retired/ as source of truth, so retired decisions drop out of grilling fuel. On-demand utility outside…
Skill Claude CodeCodex
A read-only integrity health check for forge — a deterministic script (forge-doctor.sh/.js) surveys the .forge/ state contract and docs/manifests and reports inconsistencies with severity + fix hints, exiting 0/1/2 so it doubles as an AI-free CI gate. Catches orphaned/broken state, half-sealed done/, an un-integrated…
Skill Claude CodeCodex
Seals a finished task — confirms the retro, marks STATUS.md done, archives it, empties the active .forge state, and closes the loop (which blocks the same plan from re-running). fg-done all batch-seals every already-executed task at once (retros skipped, backlog untouched, verification gate intact). Use when a task's…
Skill Claude CodeCodex
Discards incomplete (not-yet-sealed) forge work you no longer want — backlog plans, the active slot, awaiting-retro tasks, or a halted goal loop. Presents the items with a per-item risk level, then hard-delete (default) or archive to .forge/dropped/, behind a confirmation gate (already-run code is NOT reverted).…
Skill Claude CodeCodex
Toggle forge's eco mode on/off — when on: caps fg-run subagents at sonnet, activates the embedded Eco laziness-first discipline (ECO.md — code simplicity + terse output) in fg-run subagents, fg-ask grilling, and the current session, and replaces task-end handoffs (fg-run, fg-done, batch/unattended paths) with a…
Skill Claude CodeCodex
A read-only usage-help reporter for forge — /forge:fg-help prints an overview of every forge fg- skill grouped by the loop's four stages plus the outside-the-loop utilities, and /forge:fg-help prints a short usage detail (what it does · when to use · trigger · next step) for one skill. It reads each skill's own…
Skill Claude CodeCodex
After execution, classify learnings and promote them to CONTEXT.md, ADRs, and the retro log (.forge/retro), then surface the next inquiry. Always conversational; respects the promotion discipline. Use to record what you learned after a task — 'forge learn', '회고하자', '이번 작업 정리해줘'.
Skill Claude CodeCodex
Goal-driven momentum loop with bounded replan — an initial conversational inquiry pins a machine-verifiable stop condition, a fix-forward scope, and a replan cap (default 3) into .forge/loop.md, then drives tasks unattended (run → UAT → auto-skip retro → seal) until the checks pass, halting only at the walls…
Skill Claude CodeCodex
Maps the codebase with parallel subagents into structured documents under .forge/codebase/, so later grilling reads a map instead of re-exploring the code (cuts context rot). On-demand utility outside the loop. Use in contexts like "map the codebase", "analyze the codebase", "코드베이스 분석", "코드베이스 지도".
Skill Claude CodeCodex
Integrates a merged branch's forge content (.forge/branch/ /) into .forge/. Two modes: fg-merge (no arg) integrates only; fg-merge also runs git merge for you first, then integrates (default branch only; on conflict it stops, leaving the conflict in place). A deterministic script (forge-merge.sh/.js) does the git-free…
Skill Claude CodeCodex
Derives the single next step of the forge loop (reusing fg-status's state machine) and runs it — announces the step, then invokes that skill (fg-status reports; fg-next acts). One-shot by default; with the 'all' argument it drives the backlog to completion, auto-skipping retros and halting at the walls…