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.
npx agentmods add instructions/aneja5/forge-skills/claude-mdgit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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.
[](https://agentmods.dev/instructions/aneja5/forge-skills/claude-md)<a href="https://agentmods.dev/instructions/aneja5/forge-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/aneja5/forge-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04173 | $0.04173 |
| Opus 5 | $0.02086 | $0.02086 |
| Sonnet 5 | $0.00835 | $0.00835 |
| Haiku 4.5 | $0.00417 | $0.00417 |
Grade A, and why
forge-skills CLAUDE.md 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-skills
A planning-first skill library for Claude Code. Skills are structured workflows, not reference docs. Each skill encodes a specific engineering process that the agent follows step-by-step.
Project Structure
forge-skills/
├── skills/ # All skill definitions (one per directory)
│ ├── using-forge-skills/ # Meta-skill: skill discovery, pipeline, anti-rationalization
│ ├── idea-griller/ # Socratic interview → .forge/idea-brief.md
│ │ ├── SKILL.md
│ │ └── evaluation-criteria.md
│ ├── spec-driven-development/ # PRD via interview + codebase → .forge/prd.md
│ ├── architecture-and-contracts/ # System design + interface contracts → .forge/architecture.md + contracts/
│ ├── planning-and-task-breakdown/ # Task sizing + dependency graph → .forge/tasks.yaml
│ ├── incremental-implementation/ # Execute tasks.yaml one task at a time with TDD
│ ├── tdd/ # Red-green-refactor with vertical slices
│ │ ├── SKILL.md
│ │ ├── deep-modules.md
│ │ ├── interface-design.md
│ │ ├── mocking.md
│ │ ├── refactoring.md
│ │ └── tests.md
│ ├── debugging-and-recovery/ # Reproduce → localize → fix → guard
│ ├── code-review-and-quality/ # Five-axis review with contract compliance
│ ├── git-workflow/ # Atomic commits, branch strategy, PR prep
│ ├── shipping-and-launch/ # Six-domain pre-launch gate
│ ├── triage-issue/ # Bug investigation → GitHub Issue + TDD fix plan
│ ├── competitive-analysis/ # Market research → .forge/competitive.md
│ ├── gtm-strategy/ # Go-to-market plan → .forge/gtm.md
│ ├── security-and-compliance/ # Security assessment → .forge/security.md
│ ├── scalability-analysis/ # Capacity planning → .forge/scalability.md
│ ├── cross-validation/ # External review → .forge/cross-validation-*.md
│ ├── redaction-and-cleanup/ # Redact for sharing → .forge/redacted/
│ ├── api-design/ # REST conventions, error envelopes → .forge/api-design.md
│ ├── database-design/ # Schema + migrations → .forge/database-design.md + migrations-policy.md
│ ├── brand-and-identity/ # Brand essence, voice, logo, icons → .forge/brand-identity.md
│ ├── design-system/ # Tokens + components → .forge/design-system.md (soft dep on brand)
│ ├── interaction-patterns/ # Modal/sheet/expand decisions → .forge/interaction-patterns.md
│ ├── component-library/ # Component catalog → .forge/component-library.md
│ ├── page-composition/ # Page templates + responsive plan → .forge/page-composition.md
│ ├── data-visualization/ # Chart selection + color encoding → .forge/data-visualization.md
│ ├── visual-polish/ # Quality pass before demo/ship → .forge/polish-checklist.md
│ ├── parallel-execution-strategy/ # Multi-agent dispatch → .forge/parallel-plan.md
│ ├── seed-data-and-fixtures/ # Realistic data → .forge/seed-data.md
│ ├── testing-strategy/ # Test pyramid + coverage → .forge/testing-strategy.md
│ ├── error-handling-and-resilience/ # Retries + circuit breakers → .forge/error-handling.md
│ ├── observability/ # Logs + traces + alerts → .forge/observability.md
│ ├── performance-and-cost-optimization/ # Latency + cost budgets → .forge/performance-budget.md
│ ├── incident-response-and-postmortems/ # Severity + runbooks → .forge/incident-response.md
│ ├── accessibility/ # WCAG AA baseline → .forge/accessibility.md
│ ├── refactoring-and-tech-debt/ # Debt registry + strangler-fig → .forge/tech-debt-registry.md
│ ├── demo-narrative/ # Demo script + fallbacks → .forge/demo-narrative.md
│ ├── documentation-hygiene/ # README + changelog policy → .forge/docs-policy.md
│ ├── writing-skills/ # Meta-skill for contributors (TDD for skills)
│ ├── forge-sync/ # Check .forge/ artifact freshness → .forge/sync-report.md
│ ├── forge-migrate/ # Backfill forge:meta headers on legacy .forge/ files (in-place)
│ └── feedback/ # File reverse-cascade entries → .forge/feedback/*.md
├── agents/ # Specialist agent personas
│ ├── architect.md # System design, contracts, ADRs
│ ├── project-manager.md # Task breakdown, dependency ordering
│ ├── test-engineer.md # Test strategy, TDD coaching
│ ├── code-reviewer.md # PR review, contract validation
│ ├── security-auditor.md # Threat modeling, hardening
│ ├── competitive-analyst.md # Market research, positioning
│ ├── compliance-officer.md # Regulatory assessment, certification
│ ├── reliability-engineer.md # Errors, observability, incidents, performance
│ ├── data-engineer.md # Schema, migrations, query performance
│ ├── qa-engineer.md # Test strategy, quality gates
│ ├── design-engineer.md # Visual system, interaction, accessibility
│ ├── brand-strategist.md # Brand identity, voice, cross-product consistency
│ └── platform-architect.md # Multi-product boundaries, deploy topology
├── references/ # Shared checklists linked from skills
│ ├── contract-templates.md # Interface contract + ADR formats
│ ├── idea-evaluation.md # Per-branch resolution criteria for idea-griller
│ ├── testing-patterns.md # Good/bad tests, mocking rules, TDD patterns
│ ├── security-checklist.md # OWASP checklist, severity levels
│ ├── motion-system.md # Durations, curves, transitions, reduced-motion
│ └── forge-dependency-graph.md # Canonical .forge/ dependency tree (read by forge-sync)
├── commands/ # 36 slash commands for the full lifecycle
│ ├── grill.md spec.md architect.md plan.md build.md review.md ship.md
│ ├── compete.md gtm.md secure.md scale.md validate.md redact.md
│ ├── api.md db.md design.md interaction.md
│ ├── brand.md components.md pages.md dataviz.md polish.md
│ ├── parallel.md seed.md test-strategy.md
│ ├── errors.md observe.md perf.md incident.md
│ ├── a11y.md debt.md demo.md docs.md
│ ├── sync.md forge-migrate.md feedback.md
├── hooks/
│ ├── hooks.json # SessionStart hook configuration
│ └── session-start.sh # Injects using-forge-skills at every session start
├── tests/ # Pressure scenarios + RED/GREEN test results
│ ├── METHODOLOGY.md # TDD-for-skills cycle
│ ├── idea-griller/ # Test scenarios and results
│ ├── architecture-and-contracts/
│ └── spec-driven-development/
├── docs/ # Guides and explanations
├── install.sh # Single-skill installer
├── CLAUDE.md # This file
├── AGENTS.md # Intent-to-skill mapping for non-Claude-Code tools
└── README.md
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.
- 6d ago First seen · 260 lines · 4,173 tokens per session scan A e4791757927c
forge-skills CLAUDE.md is an instructions file published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 4,173 tokens to every session, about $0.0209 per session on Opus 5. 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 2026-08-31.
Other instructions, from other repositories
software-factory AGENTS.md
AGENTS.md instructions for Kripu77/software-factory, covering software factory, before you explore, skills, shipping and lanes.
the_swarm AGENTS.md
AGENTS.md instructions for ben-alkov/the_swarm, covering theswarm, structure, key files, ci and directly run linters.
the_swarm CLAUDE.md
Claude Code instructions for ben-alkov/the_swarm, a project described as: Claude Code plugin for multi-pattern multi-agent orchestration, using CC's built in Agent Swarm as the engine — dispatches and coordinates specialist sub-agents in fan-out, pipeline, map-reduce, speculative, and swarm configurations.
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
aiworkspace AGENTS.md
Instructions for a-tokyo/aiworkspace, covering ai workspace, structure, key commands, conventions and code quality.
octowiz CLAUDE.md
Instructions for raelli/octowiz, covering octowiz, releasing & deploying, commands, agent skills and issue tracker.