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/idaibin/rustzen-admin/agents-mdgit clone --depth 1 https://github.com/idaibin/rustzen-adminWhat 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 | $0.00662 | $0.00662 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
rustzen-admin 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 3d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Rules
Source of Truth
- Product positioning, direction, and module-purpose facts: docs/product/product.md.
- Current implementation facts: source code, then docs/architecture.md, then docs/guides/.
- AI contribution constraints: docs/guides/ai-coding-rules.md.
- Command source: root
justfile; inspect the target before running it.
Reading Order
- Read
README.md. - Read
AGENTS.md. - For product boundary, positioning, direction, or module-purpose decisions,
read
docs/product/product.md. - Read the nearest subdirectory
AGENTS.md. - Read only the relevant guide in
docs/guides/. - Use
docs/reference/only for deeper context.
Boundaries
- RustZen classification: Web/Rust A-class reference layout.
- Shared auth and permission capability code lives in
crates/auth/. - Shared Manifest, route, and delegation contracts live in
crates/ipc/. - Backends live in
apps/admin/,apps/monitor/,apps/insights/, andapps/reports/. - Each backend owns its migrations under its application directory.
- Frontend lives in
apps/web/. - Deployment assets live in
deploy/. - Root keeps workspace metadata, docs, command entry points, and shared crates.
- Deployment contract uses one signed
target/rz/rz-<version>-<arch>.tarbundle,/opt/rz,deploy/rz.target,deploy/rz-recovery.service, four server units, anddeploy/setup-layout.sh. - Do not apply Peripheral Vercel, Tauri client, or legacy
zen-server/zen-weblayout rules to this repository. - Do not add systemd
User/Group, hardening, or install-path permission changes without reviewingdeploy/setup-layout.shand the/optruntime directory ownership model together.
Working Rules
- Prefer the smallest viable change.
- Use
.codex/as the local task workspace. Keep unfinished cross-session handoffs under.codex/handoffs/<task-id>.mdand raw review packages, responses, ledgers, and attachments under.codex/reviews/<review-id>/; both directories are ignored. Put only explicitly requested, sanitized, durable artifacts underdocs/. - Do not add fallback or compatibility logic.
- Keep stable product decisions in
docs/product/product.md; keep stable implementation facts and rules indocs/architecture.mdanddocs/guides/. - Keep subdirectory
AGENTS.mdfiles thin. - Do not use
docs/reference/ordocs/history/as default implementation truth. - SQLite is the default storage backend.
- Update code, docs, and commands together when structure changes.
- Keep task completion tied to the task's verification commands before updating status.
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.
- 3d ago First seen · 58 lines · 662 tokens per session scan A 630ef14169c8
rustzen-admin AGENTS.md is an instructions file published in the GitHub repository idaibin/rustzen-admin (171 stars, last pushed 20d ago), licensed Apache-2.0. It adds 662 tokens to every session, about $0.0033 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
supabase studio-composition-patterns.instructions.md
Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).
supabase studio-shortcuts.instructions.md
Instructions for supabase/supabase, covering studio shortcut review rules, core principle, when to flag, preferred pattern and search inputs.
supabase studio-e2e-tests.instructions.md
Instructions for supabase/supabase, covering studio e2e test review rules, selector priority (best to worst), patterns to flag and good practices to encourage.
supabase studio-testing.instructions.md
Instructions for supabase/supabase, covering studio testing review rules, core principle, when to comment, which test type to suggest and reference.
supabase studio-copy.instructions.md
Instructions for supabase/supabase, covering studio ui copy and agent checklist (not in the design doc).
graphjin AGENTS.md
AGENTS.md instructions for dosco/graphjin, covering graphjin agent guide, architectural overview, directory structure & responsibilities, build commands and coding guidelines.