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/ancientice/palace-rs/agents-mdgit clone --depth 1 https://github.com/AncientiCe/palace-rsWrote 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.
[](https://agentmods.dev/instructions/ancientice/palace-rs/agents-md)<a href="https://agentmods.dev/instructions/ancientice/palace-rs/agents-md"><img src="https://agentmods.dev/badge/instructions/ancientice/palace-rs/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01400 | $0.01400 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
palace-rs 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 4d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules
When working on this codebase, follow these rules on every task.
1. Test-Driven Development (TDD)
- Write behavioural tests first. Define the expected behaviour in tests before implementing.
- See them fail. Run the test suite and confirm the new tests fail (red).
- Implement. Write the minimum code to make the tests pass.
- See them pass. Run the test suite and confirm all tests pass (green).
Do not implement behaviour without a failing test that defines it.
2. Quality Gates on Every Task
Before considering a task done, ensure all of the following pass:
cargo fmt— code is formatted.cargo clippy --all-targets --all-features -- -D warnings— no clippy warnings or errors.cargo audit— no known security advisories in dependencies.cargo test --all-features— full test suite passes.- Pipelines pass — check pipeline steps that can be run locally and make sure they pass.
Match CI locally with the exact commands above (see .github/workflows/ci.yml).
Fix any failure before marking the task complete.
3. No Plan Markdown Files
- Do not create
.mdfiles for plans (e.g.PLAN.md,TODO.md, task plans). - Create markdown only for documentation (API, README, runbooks, etc.) when necessary.
- Keep planning in conversation, tickets, or code comments—not as standalone plan documents in the repo.
4. Internal API Discipline
- palace-rs is a CLI/MCP tool: it ships to users as compiled binaries via the Homebrew
tap, the install script, and the MCP registry
.mcpbbundle. - Internally, the crate is split into a
[lib](thePalacefacade insrc/palace.rs) and a[[bin]](src/cli.rs, behind theclifeature flag). The CLI and the MCP server (src/mcp_server.rs) both build on that internal API, so keep it clean and minimal for maintainability. - Before changing public types, functions, or module structure, consider: the CLI and MCP server call sites, SQLite schema migrations, and embedding model compatibility.
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.
- 4d ago First seen · 121 lines · 1,400 tokens per session scan A c84ec6380435
palace-rs AGENTS.md is an instructions file published in the GitHub repository AncientiCe/palace-rs (4 stars, last pushed 3d ago), licensed MIT. It adds 1,400 tokens to every session, about $0.0070 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
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
gno AGENTS.md
AGENTS.md instructions for gmickel/gno, covering knowledge cutoff warning, apis - bun first!, must use bun, acceptable node:\ (no bun equivalent) and testing.
cortex CLAUDE.md
Instructions for gzoonet/cortex, covering claude.md — gzoo cortex project instructions, what is gzoo cortex, tech stack, monorepo structure and architecture rules.
loomem CLAUDE.md
Instructions for vvooki-sys/loomem, covering claude.md — rules for ai code generators in the loomem repo, router — read the subset that applies, five hard rules (never break these), build & run and repo map (where things live).
trinity AGENTS.md
AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-09-02 03:21:12，snapshot 任务自动刷新）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.
aionforge-memory AGENTS.md
Instructions for jscott3201/aionforge-memory, covering agent guide for aionforge memory, start here, workspace layout, core invariants and running locally.