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/rvbernucci/forja-guide/agents-mdgit clone --depth 1 https://github.com/rvbernucci/forja-guideWrote 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/rvbernucci/forja-guide/agents-md)<a href="https://agentmods.dev/instructions/rvbernucci/forja-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/rvbernucci/forja-guide/agents-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 | $0.00341 | $0.00341 |
| Opus 5 | $0.00170 | $0.00170 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
forja-guide AGENTS.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.
What it actually says
Agent Operating Contract
This file applies to every coding agent operating in this repository.
Mission
Build Forja as a governed, auditable, interoperable multi-agent software factory. Preserve the distinction between architecture, implemented behavior, generated evidence, and future plans.
Required Behavior
- Read
README.md,ROADMAP.md, and the relevant architecture documents before changing implementation contracts. - Treat JSON schemas in
schemas/as language-neutral public interfaces. - Add or update an ADR when a decision changes system boundaries, persistence, trust, security, or protocol compatibility.
- Keep all examples free of real credentials, private hostnames, customer data, personal paths, and production identifiers.
- Use one author per file or artifact during concurrent work.
- Preserve provenance for generated artifacts and never edit generated evidence manually.
- Run
make validatebefore declaring work complete.
Forbidden Behavior
- Do not copy private product repositories into this public project.
- Do not commit
.envfiles, tokens, passwords, private keys, database dumps, raw chats, or production logs. - Do not present Qdrant similarity as authority.
- Do not create Neo4j edges from embeddings without explicit evidence and a promotion rule.
- Do not let an LLM directly mutate production state without authorization, validation, and an audit event.
- Do not mark planned capabilities as implemented.
Authority Hierarchy
runtime evidence and tests
> source code, schemas, and migrations
> deterministic indexes and lineage
> curated graph relations
> active architecture contracts
> semantic retrieval
> chat memory
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 · 49 lines · 341 tokens per session scan A b3a5b7ebfd2e
forja-guide AGENTS.md is an instructions file published in the GitHub repository rvbernucci/forja-guide (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 341 tokens to every session, about $0.0017 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
agiwo AGENTS.md
Instructions for xhwSkhizein/agiwo, covering agents.md, how to use this file, truth source order (adr 0048 / 0049), logging and config hot reload.
Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale AGENTS.md
Instructions for microsoft/Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale, covering ai agent guidelines, 🔒 security best practices, 📋 repository guidelines, purpose and what not to modify without permission.
Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale copilot-instructions.md
Instructions for microsoft/Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale: This is a Microsoft Build 2026 session content repository.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.