trueforge: Instructions file for Codex

AGENTS.md

trueforge AGENTS.md is an instructions file for Codex, OpenCode from truefoundry/trueforge. It costs 1,451 tokens per session, scanned A, original, MIT.

Repository guidance for TrueFoundry, an open-source runtime that turns a language model into a working software agent.

In plain words
What is it for?
Use it when changing TrueFoundry packages, frontend code, CI configuration, Docker Compose services, SDK releases, or workspace workflows.
Why use it?
It records project rules for scripts, continuous integration, package releases, shared services, and published-package changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is truefoundry/trueforge's own configuration. It tells Codex and OpenCode how to work on trueforge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trueforge configures →

About the project

TrueForge is an agent runtime that runs the execution loop connecting language models, tools, skills, sandboxes, approvals, context handling, and session state. Developers use it through a chat interface, HTTP API, TypeScript SDK, or embeddable UI to build and operate AI agents.

truefoundry/trueforge · 6,443 stars · on GitHub · trueforge.dev

Reuse

Borrowing it

Nothing to install: this file belongs to truefoundry/trueforge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/truefoundry/trueforge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/truefoundry/trueforge

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for trueforge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/truefoundry/trueforge/agents-md/github.svg)](https://agentmods.dev/instructions/truefoundry/trueforge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/truefoundry/trueforge/agents-md"><img src="https://agentmods.dev/badge/instructions/truefoundry/trueforge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for trueforge AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/truefoundry/trueforge/agents-md"><img src="https://agentmods.dev/badge/instructions/truefoundry/trueforge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,451 This file is loaded in full into every session.
When invoked 1,451 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01451 $0.01451
Opus 5.5 $0.00580 $0.00580
Sonnet 5.5 $0.00290 $0.00290
Haiku 4.5 $0.00145 $0.00145

Measured 10d ago against content hash d40cd0259f7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trueforge 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 10d 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.

AGENTS.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  • Workspace tasks MUST use package.json scripts; add a script when a missing workflow is repeatable like the existing commands, not ad hoc commands.
  • CI package path filters, matrix package ids, and root scripts test:* in .github/workflows/ci.yml and root package.json MUST stay synchronized when a workspace package is added, renamed, or moved; the store filter sync rule lives in packages/trueforge-core/src/agent-session/store/AGENTS.md.
  • Release wiring MUST keep dist-free host development, pnpm smoke, packed CJS/ESM consumers of @truefoundry/trueforge-core, and ESM consumers of @truefoundry/trueforge-sdk working without changes. Workspace loaders opt into SDK/core src/ via the trueforge-dev export condition (never "development"); the SDK's trueforge-dev types MUST stay on generated .d.mts from sdk:types (source is not exactOptionalPropertyTypes-clean).
  • PRs that change published-package code (packages/assistant-ui-runtime, packages/trueforge-core, packages/trueforge, packages/trueforge-ui, packages/trueforge-sdk) or packages/frontend (ships inside @truefoundry/trueforge) MUST include a new .changeset/*.md file (pnpm changeset). Docs, CI/workflows, charts, and docker-compose changes do not. SDK regeneration already adds @truefoundry/trueforge-sdk via pnpm changeset:sdk-regen.
  • Changeset bumps MUST be patch only. Minor (and major) version bumps are controlled by an external release process; PR changesets MUST NOT use minor or major.
  • Shared Postgres/Redis settings in docker-compose.yml and docker-compose.dev.yml (image versions, health checks, env_file) MUST stay synchronized; intentional differences (app services, data paths, project name, host ports, in-network POSTGRES_HOST / REDIS_URL) MUST stay explicit. packages/trueforge/.env is the host-dev + secrets source; docker-compose.yml may read it but MUST override container connectivity so host-dev localhost values are not used inside the smoke-test stack.
  • Changes to types or schemas MUST keep packages/trueforge-core, packages/frontend, packages/trueforge, and patches synchronized; they MUST NOT update only one affected layer.
  • TypeScript code MUST NOT use assertion escapes such as as T, as unknown as T, non-null !, or as never to silence type errors; implementations MUST use sound contracts, guards, or corrected types.
  • When catching an error and throwing another, the new error MUST set { cause: caught } so the original failure is preserved for logs and debugging.
  • Every type, schema, helper, and contract MUST have one canonical owner; code MUST NOT introduce duplicate definitions or forwarding shims that hide ownership.
  • AgentUIServer / server-port types (AgentChatServer, AgentBuilderServer, catalog ports, session/turn DTOs, stream events) MUST be defined only in packages/assistant-ui-runtime/src/server/types.ts / events.ts. @truefoundry/trueforge-ui MUST re-export them from src/server/types.ts (pass-through aliases only) and MUST NOT add hand-written parallel definitions of those ports/DTOs.
  • Runtime types backed by Zod schemas MUST be derived with named z.infer<typeof Schema> aliases; code MUST NOT duplicate those schemas as hand-written interfaces or indirect utility-type chains.
  • Modules MUST use static import and import type; they MUST NOT use require(), require.resolve(), or lint suppressions to bypass import checks.
  • After editing ESLint-covered files, run pnpm exec eslint <changed-files> --max-warnings=0 and fix findings in the same change. Do not drop async solely to silence @typescript-eslint/require-await when the body can throw: keep Promise rejections via Promise.resolve() / Promise.reject() / Promise.resolve().then(...).
  • A change that makes code unused MUST remove that dead code in the same change; it MUST NOT leave stale exports, files, documentation, duplicates, or “just in case” shims.
  • Every nested AGENTS.md MUST have a sibling CLAUDE.md containing only @AGENTS.md, so Cursor and Claude Code load the same scoped rules.
  • OpenAPI specs under .github/fern/openapi/openapi.json and docs/openapi.json are autogenerated in CI and MUST NOT be edited manually (both copies MUST stay identical)
  • Code under packages/trueforge-sdk and python/trueforge_sdk is autogenerated in CI and MUST NOT be edited manually
  • Tests MUST live under a package-top-level test or tests directory that mirrors the src layout; they MUST NOT be inlined under src.
  • Functions with more than one parameter of the same type MUST take a single options object (e.g. f({ a, b }: { a: string; b: string })); they MUST NOT use multiple positional parameters of that repeated type (e.g. f(a: string, b: string)).
  • Zod unions MUST use z.discriminatedUnion whenever every member carries a shared literal discriminator field; z.union is only permitted when no such common discriminator exists.
  • HTTP/OpenAPI wire shapes (path params, query params, request/response JSON fields) and database identifiers (table/column names, persisted jsonb document keys) MUST use snake_case.
  • Server code MUST NOT read environment variables via process.env directly; all env reads MUST go through packages/trueforge/src/config.ts, unless there is a documented special requirement (for example bootstrap before config is loaded).
  • UI styles MUST use rem for lengths (not px); assume 1rem = 16px. Prefer Tailwind spacing/type scale utilities when they fit. Exceptions: 0px in calc()/env() fallbacks, existing media-query breakpoints, and canvas/measurement APIs that require CSS pixels.

Read the full file on GitHub · 33 lines

Changes

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.

  1. 10d ago Changed · -5 tokens per session d40cd0259f7e
  2. 20d ago Changed · +1 lines · +78 tokens per session ed247d633a0a
  3. 1mo ago Changed · +1 lines · +39 tokens per session 1165244aa11d
  4. 1mo ago Changed · +2 tokens per session 130bd3982734
  5. 1mo ago Changed · +8 tokens per session b2e9b72c27e0
  6. 2mo ago Changed · +1 lines · +70 tokens per session 2fecae8550e4
  7. 2mo ago Changed · +7 lines · +108 tokens per session e133bf6b08f2
  8. 2mo ago Changed · +81 tokens per session cf6eb954c1d3
  9. 2mo ago First seen · 23 lines · 1,070 tokens per session scan A e685cd2cffae

Subscribe to this mod's changes

trueforge AGENTS.md is an instructions file published in the GitHub repository truefoundry/trueforge (6,443 stars, last pushed yesterday), licensed MIT. It adds 1,451 tokens to every session, about $0.0058 per session on Opus 5.5. 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.

Related

trueforge AGENTS.md compared with instructions from other repositories

trueforge AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
trueforge AGENTS.mdtruefoundry/trueforgeInstructions file6.4kyesterdayMITA1,451Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode