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/lylemi/dsh-codex-app-server/agents-mdgit clone --depth 1 https://github.com/LyleMi/dsh-codex-app-serverWhat 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 | $0.00684 | $0.00684 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
dsh-codex-app-server 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Production TypeScript lives in src/. Top-level modules cover agent lifecycle, configuration, process management, and DSH bindings; JSONL transport and App Server handling are under src/wire/, while session projection is under src/projection/. Tests are flat tests/*.spec.ts files, with the opt-in real Codex smoke test at tests/real-codex.e2e.ts. Protocol recordings belong in tests/fixtures/app-server/ and must be scrubbed of credentials, account data, tokens, and home paths. Design and security rationale live in docs/; maintenance scripts live in scripts/. Generated lib/ and coverage/ output must not be committed.
Build, Test, and Development Commands
Use Node.js 22.19+ and pnpm 10.15.0.
corepack enable && pnpm install --frozen-lockfileinstalls the locked toolchain.pnpm buildcompilessrc/intolib/.pnpm testruns the Vitest suite once;pnpm test:coverageenforces coverage.pnpm typecheck,pnpm lint, andpnpm format:checkrun focused static checks.pnpm protocol:checkverifies the installed Codex App Server contract against the reviewed fixture.pnpm checkruns the complete merge/release gate, including Reforge and package validation.RUN_REAL_CODEX=1 pnpm test:e2eruns the credential-isolated real CLI smoke test when Codex is available.
Coding Style & Naming Conventions
Follow Prettier output: two-space indentation, single quotes, and no semicolons. Keep TypeScript strict and use import type for type-only imports. Name files with lowercase descriptive nouns (for example, wire/transport.ts); use PascalCase for types/classes and camelCase for functions and variables. Preserve explicit ownership, bounded resources, and fail-closed protocol behavior.
Testing Guidelines
Use Vitest and name unit/integration tests tests/<area>.spec.ts. Add regression coverage beside the affected boundary. V8 thresholds are 80% for lines, functions, and statements, and 70% for branches. Protocol changes require pnpm protocol:check, sanitized fixtures, compatibility documentation, and the real smoke test when credentials are safely available.
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 · 30 lines · 684 tokens per session scan A d6878fd1e00d
dsh-codex-app-server AGENTS.md is an instructions file published in the GitHub repository LyleMi/dsh-codex-app-server (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 684 tokens to every session, about $0.0034 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
airelay CLAUDE.md
Claude Code instructions for ligj1706/airelay, covering claude.md, 项目概述, 产品定位, 设计原则 and 产品演进方向.
kungfu AGENTS.md
AGENTS.md instructions for kungfu-systems/kungfu, covering agents.md, start from the person's objective, rules that always apply, load bounded context before changing the repository and execute and verify through shifu.
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.
dsh-worktable AGENTS.md
Instructions for Aisland-SJL/dsh-worktable, covering dsh-worktable 项目规则, 协作方式（用户定案，最高优先级）, 边界, 构建与验证 and 领域约定（会话中必须遵守）.
zero2Agent AGENTS.md
Instructions for ranxi2001/zero2Agent, covering zero2agent repository guide, purpose, start every task, source of truth and repository skills.
dart_agent_core AGENTS.md
Instructions for memex-lab/dart_agent_core, covering agents.md, common commands, transcript viewer cli (reads eval traces), two public libraries and architecture (big picture).