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/quaywin/agys/agents-mdgit clone --depth 1 https://github.com/quaywin/agysWrote 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/quaywin/agys/agents-md)<a href="https://agentmods.dev/instructions/quaywin/agys/agents-md"><img src="https://agentmods.dev/badge/instructions/quaywin/agys/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 5.1 | $0.00476 | $0.00476 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade B, and why
agys AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Keep `go vet ./...` clean without warnings. Copies of this mod
1 near-identical copy found in the catalogue:
- agys GEMINI.md — 100% identical, 0 lines differ
What it actually says
AGENTS.md — Development Guidelines for agys
⚠️ Critical Binary Deployment Rule
[!CAUTION] NEVER copy, build, overwrite, or delete the binary at
/Users/quaywin/.local/bin/agysdirectly during agent tasks. (e.g.cp ... /Users/quaywin/.local/bin/agys,go build -o /Users/quaywin/.local/bin/agys,rm /Users/quaywin/.local/bin/agys).Reason: Overwriting a live executable binary on macOS while active terminal panes, background watchers, or Herdr hooks are running will corrupt running process mappings and trigger an instant kernel SIGKILL (
[1] <PID> killed agys).
✅ Allowed Build & Test Procedures
- Local Build & Test:
go build ./... go test -v ./... - Local Binary in Repository:
go build -o ./bin/agys . - Go Install (Standard):
(Installs safely togo install .$GOPATH/bin/agyswithout touching the system path).
🛠️ Project Architecture & Best Practices
- Language: 100% Pure Go (Zero Python / pip / asdf / shims dependency).
- Herdr Integration:
cmd/herdr_hook.go: Cobra subcommandagys herdr-hook [session|quota].pkg/profile/herdr.go: Lifecycle hook handler, socket RPC, compact sidebar badge (FormatModelAbbreviation), and Window Title (5H&Weeklyquota).pkg/profile/quota.go:GetProfileFullQuotaDetailsForModelwith token-based dynamic matching and 3-tier fallback.
- Model Resolution Order:
Explicit -m/--model arg->Live prompt transcript (USER_SETTINGS_CHANGE)->.active_model cache->settings.json->default Gemini. - Quality Assurance:
- Always run
go test ./...and ensure zero test failures before completing tasks. - Keep
go vet ./...clean without warnings.
- Always run
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 · 41 lines · 476 tokens per session scan B 3ebf895b4a5d
agys AGENTS.md is an instructions file published in the GitHub repository quaywin/agys (10 stars, last pushed yesterday), licensed MIT. It adds 476 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
unraid-management-agent copilot-instructions.md
Copilot instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
free-ai-gateway AGENTS.md
Instructions for zaber-dev/free-ai-gateway, covering 🤖 free-ai gateway - agentic development guidelines, 🏛️ monorepo architecture & package boundaries, 🛑 strict architectural rules for agents, 💻 essential developer commands and build all packages across monorepo.
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.
ksail go-code.instructions.md
Use when writing or editing Go source files in the KSail codebase. Covers error handling, path safety, dependency guard, and package organization conventions.