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/csabakovacs/rulesmith/agents-mdgit clone --depth 1 https://github.com/CsabaKovacs/rulesmithWhat 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 | $0.01879 | $0.01879 |
| Opus 5 | $0.00940 | $0.00940 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
rulesmith 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Conventions (Evidence-Backed)
Execution Contract
- BINDING: This rulebook is mandatory. Every rule, convention, and workflow defined here MUST be followed without exception. Skipping, ignoring, or partially applying rules is a violation. If a rule conflicts with your default behavior, the rulebook takes precedence.
- Use evidence-first behavior: every non-trivial claim or new convention must stay tied to concrete repository evidence.
- Enforce repository conventions first; do not replace a strong local pattern with generic best-practice text.
- Keep changes reviewable and scoped: prefer the smallest behavior-safe diff that fits the touched boundary.
- strictness:
very-strict - standards:
project-plus-standard
Project Snapshot
- What: rulesmith — local-first CLI + MCP server for evidence-backed AI coding instruction generation. (evidence: package.json)
- Stack: TypeScript monorepo managed by pnpm with 3 workspace packages. (evidence: pnpm-workspace.yaml, tsconfig.base.json)
- Packages:
packages/core— scanner, evidence bundler, rulebook builder, AST analysis, template renderer, decision tree engine, pack system, safe FS utilities. (evidence: packages/core/src/index.ts)packages/cli— Commander-based CLI wrapping core functions. (evidence: packages/cli/src/index.ts)packages/mcp— MCP server wrapping core functions via@modelcontextprotocol/sdk. (evidence: packages/mcp/src/server.ts)
- Key directories:
packs/default/— Handlebars templates + decision tree YAML + orchestrator prompts. (evidence: packs/default/pack.json)examples/fixtures/— Test fixture repos. Test data, NOT production code. (evidence: examples/fixtures/)
- Build command coverage: install=yes, build=yes, test=yes, lint=yes. (evidence: package.json)
Setup Commands (with evidence)
- install:
pnpm install - build:
pnpm -r build - test:
pnpm -r test - lint:
pnpm -r lint - format:
UNKNOWN - dev:
UNKNOWN
Evidence: package.json, pnpm-workspace.yaml
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 · 129 lines · 1,879 tokens per session scan A 645eb8499ea3
rulesmith AGENTS.md is an instructions file published in the GitHub repository CsabaKovacs/rulesmith (15 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,879 tokens to every session, about $0.0094 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.