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/truefoundry/aitori/agents-mdgit clone --depth 1 https://github.com/truefoundry/aitoriWhat 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 | $0.01179 | $0.01179 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
aitori 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for contributors and coding agents working in this repo. User-facing docs live in README.md and docs/.
Layout
cmd/aitori/ CLI entrypoint (cobra)
internal/
config/ schema, load/validate, defaults, managed overlay
hostmatch/ host-pattern matcher (exact, *.x, .suffix)
token/ token-file reader + fsnotify watcher + cache
ca/ per-device CA + on-the-fly leaf certs
classify/ rules engine + body heuristics (llm | mcp | other)
circuit/ gateway circuit breaker
router/ the reroute rewriter (x-tfy-* headers, dial redirect)
appresolve/ flow -> app attribution (bundle/exe/process/host)
pipeline/ resolve -> classify -> action (reroute | passthrough)
proxy/ selective-MITM server, splice, streaming forward, fail-open
adapter/ OS interface + build-tagged impls (darwin/linux/windows)
clientcfg/ patches client config (Claude Code settings.json) on up/down
sysuser/ SUDO_USER-aware home/uid resolution (single source of truth)
inject/ sink/ capture/ Tier-0 injectors, observability sinks, exchange records
profiles/ embedded built-in app profiles (//go:embed)
tools/aitori-gateway/ SEPARATE Go module: a local gateway with OTel->SQLite
tracing and a trace UI, for testing/demos
configs/ example + test configs
test/integration/ end-to-end tests (gateway + fake upstream + SSE)
Multi-module repo + the CGO rule
Two Go modules:
- root (
github.com/truefoundry/aitori) — the agent. Stays dependency-light. tools/aitori-gateway— its own module; carries the heavier OTel + SQLite deps so they never reach the agent.
Always build and test with CGO_ENABLED=0. A transitive gopsutil dependency
(go-m1cpu) crashes at init under cgo on recent Go/macOS. The Makefile sets
this for you; if you invoke go directly, set it yourself. The gateway uses the
pure-Go modernc.org/sqlite driver for the same reason.
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 · 103 lines · 1,179 tokens per session scan A 9364cc27d9e8
aitori AGENTS.md is an instructions file published in the GitHub repository truefoundry/aitori (48 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,179 tokens to every session, about $0.0059 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
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.