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/woai3c/x-code-cli/agents-mdgit clone --depth 1 https://github.com/woai3c/x-code-cliWhat 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 | $0.01995 | $0.01995 |
| Opus 5 | $0.00997 | $0.00997 |
| Sonnet 5 | $0.00399 | $0.00399 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
x-code-cli 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This is the repository instruction entrypoint. X-Code loads the applicable AGENTS.md chain into project context;
other agent hosts must use a verified discovery path or open this file explicitly. Keep it concise because it is prompt
context.
Rules
- Use visualizations when they help explain complex concepts.
- Keep responses concise and direct, and clearly distinguish facts from assumptions.
- Base research on reliable sources.
- Stay aligned with the user's goals and constraints.
- Avoid unnecessary questions; ask only when a key decision requires confirmation.
- Use sub-agents judiciously and avoid unnecessary parallelism.
- Keep code changes minimal and avoid unrelated refactoring.
- Verify actual results through testing; do not assume something is complete just because it looks complete.
- Keep all features and tests compatible with Windows, macOS, and Linux. Do not assume POSIX paths, shells, signals, terminal glyphs, process behavior, or file-lock semantics. Platform-conditional tests are allowed only when the underlying capability cannot be tested equivalently, and the reason must be explicit.
- Protect existing code and data.
- Report key results without unnecessary progress updates.
Commands
pnpm workspace; Node >= 22.
pnpm build # tsc -b (core) then esbuild (cli → dist/cli.js)
pnpm dev # build core, then run CLI from source via tsx (no watch)
pnpm typecheck # tsc -b — strict, run before any PR
pnpm lint # eslint --fix; ignores **/tests/** and *.js
pnpm test # build + Unit/Fault/Package/PTY tests
pnpm test <pattern> # single file: pnpm test packages/core/tests/agent-loop.test.ts
pnpm run ci # typecheck + lint/format checks + pnpm test
After editing core sources you must pnpm build (or tsc -b --watch in packages/core). The CLI imports packages/core/dist/, not the TS source.
Delivery workflow
Follow docs/development/agent-workflow.md for work definition, Human Plan Review, verification evidence, Human Local Acceptance, Draft/Ready PR handling, and continuous knowledge capture. Use .github/pull_request_template.md for the durable PR handoff. Capability status in that guide describes what can run; every task must report its own check outcomes separately.
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 · 94 lines · 1,995 tokens per session scan A d65e6c909940
x-code-cli AGENTS.md is an instructions file published in the GitHub repository woai3c/x-code-cli (47 stars, last pushed 2d ago), licensed MIT. It adds 1,995 tokens to every session, about $0.0100 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
teaql-agent-kit AGENTS.md
Instructions for teaql/teaql-agent-kit, covering agents.md — teaql agent kit and hard requirements.
FylloCode AGENTS.md
Instructions for Fioooooooo/FylloCode, covering agents.md, 项目概述, 技术栈, 目录结构 and 常用命令.
alint AGENTS.md
Instructions for moeru-ai/alint, covering alint agent guide, structure & responsibilities, commands (pnpm with filters), development practices and testing practices.
lunar AGENTS.md
Instructions for gszr/lunar, covering how to work here, our goals, before you type, code and scope.
ZenCODE AGENTS.md
Instructions for gerardogrisolini/ZenCODE, covering agents.md, project, build and validation, linux validation and test and state conventions.
baro CLAUDE.md
Claude Code instructions for jigjoy-ai/baro, covering claude.md, project overview, tech stack, directory structure and build commands.