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/stackoverworld/primer-ai/agents-mdgit clone --depth 1 https://github.com/stackoverworld/primer-aiWhat 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 | $0.01367 | $0.01367 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
primer-ai 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Mission
- Project:
primer-ai - Goal: Build primer-ai with an agent-optimized architecture and reproducible delivery workflow.
- Stack focus: TypeScript + Node.js
- Shape: Cli Tool
- Target coding assistants: codex
Always-Loaded Rules
- Treat this file as the routing layer, not the full handbook.
- Pull detailed guidance from
docs/index.mdbefore major design changes. - Keep edits scoped; avoid unrelated cleanup unless explicitly requested.
- Prefer deterministic checks over prose-only guidance.
- Update docs when architecture or contracts change.
- Keep responses concise, concrete, and verifiable.
- Prefer invoking project automation over manual style enforcement.
Progressive Disclosure Map
docs/index.md: source-of-truth index for project knowledge.docs/architecture.md: bounded contexts, module boundaries, dependency direction.docs/api-contracts.md: contracts, schemas, and compatibility policy.docs/conventions.md: coding, testing, and collaboration standards.docs/maintenance.md: verification pipeline, context budget, and freshness policy.docs/skills.md: curated skill inventory and trigger discipline.docs/decisions/*.md: ADR history.docs/runbooks/local-dev.md: environment setup and local operation guide.skills/**/SKILL.md: reusable task playbooks loaded only when relevant.src/commands/AGENTS.md: Command UX, validation, and error ergonomics. (applies insidesrc/commands/).src/core/AGENTS.md: Core orchestration and side-effect boundaries. (applies insidesrc/core/).tests/AGENTS.md: End-to-end command scenarios and edge cases. (applies insidetests/).
Harness Adapters
- Codex chain behavior: root
AGENTS.md+ deeper scoped files are intentionally concise to avoid context truncation. - Claude-specific adapter files are omitted because Claude target was not selected.
- Cursor adapters were skipped in this initialization.
- Architecture draft source: codex output normalized into deterministic templates.
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.
- yesterday First seen · 100 lines · 1,367 tokens per session scan A 054eb8bd0c1a
primer-ai AGENTS.md is an instructions file published in the GitHub repository stackoverworld/primer-ai (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,367 tokens to every session, about $0.0068 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
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.