mcpField
F
forge

forge

github.com/redteamlifeAgent workflows139 installsUpdated 12w ago
Repository

About forge

FORGE is a governed workflow skill for bounded implementation, planning, review, and delivery. It routes tasks to focused procedures, limits loaded context, and uses evidence-based checkpoints and explicit stop conditions.

Key features

  1. 01Task-specific workflow routing
  2. 02Bounded work with checkpoints
  3. 03Context-aware document loading
  4. 04Evidence and completion checks
  5. 05Parallel team-work guidance

Use cases

  1. 01Planning and implementing a scoped task
  2. 02Reviewing security and task evidence
  3. 03Preparing a release or handoff

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/redteamlife/forge --skill forge

After installing, type/forgein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

assets/agent-surfaces/
AGENTS.md
assets/agent-surfaces/.claude/
settings.forge-fragment.json
assets/agent-surfaces/.codex/
hooks.json
assets/agent-surfaces/.cursor/rules-scoped/
go-backend.mdc
js-frontend.mdc
project-conventions.mdc
python-backend.mdc
security.mdc
assets/agent-surfaces/.cursor/rules/
forge.mdc
assets/agent-surfaces/.github/
copilot-instructions.md
assets/agent-surfaces/.windsurf/rules/
forge.md
assets/application-docs/
architecture-overview.md
deployment-playbook.md
developer-guide.md
incident-runbook.md
interfaces-and-protocols.md
threat-model.md
tool-overview.md
assets/application-docs/adr/
0001-record-architecture-decisions.md
README.md
assets/ci-setup/
github.md
gitlab.md
assets/ci/docs/
commit-format.md
governance-patterns.md
validators.md
assets/ci/gitlab/
security.gitlab-ci.yml
assets/ci/hooks/
commit-msg
pre-commit
pre-push
assets/ci/policy/
forge-org-policy.template.yaml

Details

From the project README

FORGE

FORGE is an explicit workflow for bounded work: one task, clear scope, hard stops, evidence, and clean checkpoints.

Use it for governed implementation, planning, review, shipping, coordination, or context-safe bootstrap.

Routing

  • Bootstrap or migrate docs: forge-bootstrap
  • Plan lifecycle work: forge-plan
  • Build/implement a task: forge-build or forge-execute-task
  • Review work: forge-review
  • Ship, release, or close out: forge-ship
  • Critique scope and assumptions: forge-critique
  • Run security review: forge-security-review
  • Check done/evidence: forge-evaluation
  • Read/update lessons: forge-memory
  • Manage private/public tool releases: forge-tool-workflow
  • Coordinate multi-repo shared-contract work: forge-cross-project

Read references only when the current task requires them:

  • team and branches: references/team-mode.md
  • repo flavors: references/repo-flavors.md
  • agent surfaces: references/agent-flavors.md
  • DevSecOps gates: references/devsecops-gates.md
  • app docs: references/application-docs.md
  • lifecycle map: references/lifecycle-map.md
  • skill anatomy: references/skill-anatomy.md
  • context and token discipline: references/token-efficiency.md

Operating Model

  1. Read the minimum project-local context needed for the current step.
  2. Prefer docs/forge/CONTEXT.md when present; otherwise use conservative lite defaults.
  3. Read docs/forge/AI.md, the compact task index or configured task source, one selected task, and task-relevant source files.
  4. Do not load all FORGE docs, all tasks, all memory, or all security checklists at startup.
  5. Preserve one bounded checkpoint at a time: implementation, evidence, task state, and commit or PR/MR handoff.
  6. Stop on ambiguity, missing prerequisites, architecture conflict, unsafe operations, unresolved security concerns, or failed gates.
  7. Activation follows activation_mode; repo-default routing requires that consent.

Team Mode

When multiple developers or agents work in parallel:

  • use feature branches rather than direct work on shared branches
  • claim one task before implementation
  • require explicit file_scope for executable tasks
  • prefer issue assignment and labels when GitHub or GitLab is authoritative
  • use append-only evidence and memory records where possible
  • require CI and protected-branch merging

Output Discipline

Follow progress_policy in docs/forge/AI.md (default compact when absent): concise checkpoint output, detailed blockers, one terminal summary — never per-task recaps of what the task file and commit already record. Full protocol: references/checkpoint-output.md.

Comments

Markdown supported