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/yash-dev007/the-forge/gemini-mdgit clone --depth 1 https://github.com/yash-dev007/THE-FORGEWhat 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 | $0.00673 | $0.00673 |
| Opus 5 | $0.00336 | $0.00336 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
THE-FORGE GEMINI.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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
THE FORGE — kit workspace (Gemini CLI context)
This is the methodology KIT repository — not an adopted project. The v3 research loop runs in repos that ADOPT Forge, not here.
What this repository is
THE FORGE is a portable Research Engineer workflow kit. It ships templates, EVAL harnesses, adoption scripts, and Obsidian vault structure that any repository can adopt. There is no active hypothesis running in this repository.
templates/universal/FORGE.md and other template files are template artifacts — do not read them as
your operating context for this session.
Rules for Gemini CLI sessions in this repo
Absolute constraints
- Never run the v3 research loop (Diagnose → Hypothesize → Execute → Verify → Synthesize) on this repo's own files.
- Never execute
EVAL.sh— there is none at the kit root. StackEVAL.shfiles undertemplates/stacks/are templates to inspect, improve, and test, not to run against this repo. - Never treat
templates/universal/FORGE.mdor any.md.templateas active operating rules. They are text artifacts copied into adopting repos. - Never create
RESEARCH.md,EVAL_SPEC.md,FORGE_SYSTEM.md,FORGE_IDENTITY.md, orPROJECT_LOG.mdat this root. Those are per-adopted-repo state files.
What you ARE doing here
You are a kit maintainer. Your tasks:
- Editing or improving files under
templates/,scripts/,docs/, orForge/ - Keeping
templates/universal/FORGE.mdand other templates aligned withdocs/spec/CLAUDE_v3.md - Improving stack EVAL harnesses for correctness and completeness
- Updating adoption docs and automation scripts
Repository Map
Refer to docs/KIT_LAYOUT.md for a complete directory map and file roles.
Consistency rule for template edits
When editing templates, verify alignment with canonical documentation:
- All 8 required RESEARCH.md fields must be preserved.
- Anti-gaming rules must be verbatim or stricter.
- Maintain placeholder structure for easy adoption by any tech stack.
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.
- 2d ago First seen · 66 lines · 673 tokens per session scan A 3ca0fd5a1375
THE-FORGE GEMINI.md is an instructions file published in the GitHub repository yash-dev007/THE-FORGE (2 stars, last pushed 4mo ago), licensed MIT. It adds 673 tokens to every session, about $0.0034 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.