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/stroops/sloop/agents-mdgit clone --depth 1 https://github.com/stroops/sloopWhat 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 | $0.00300 | $0.00300 |
| Opus 5 | $0.00150 | $0.00150 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
sloop 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 yesterday.
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.
What it actually says
AGENTS.md
Provider-aware architecture (read before adding provider behavior)
Sloop's reason to exist is multi-AI-provider support, so the codebase is provider-aware by
design: all per-provider knowledge lives in the adapter manifest (internal/adapter/builtin/ <tool>.yaml, user-overridable in ~/.sloop/adapters/), and every provider-aware feature reads it.
The rule: never hardcode a tool name in a feature. Add capability to the manifest instead.
Detect, launch, context delivery, skills, hooks, and completion are all manifest-driven. To support a
new CLI, drop in one <tool>.yaml; no Go changes unless it needs a brand-new mechanism.
- Provider contract + manifest schema:
docs/reference/ADAPTERS.md - Config layering (unified user config vs per-provider manifests):
docs/reference/CONFIG.md - Runtime capability matrix:
sloop tools
User config is unified (one local .sloop/config.yaml + one global ~/.sloop/config.yaml +
the global DB), never split per provider.
Development workflow
- Always run
make lint,make test, andgo test -v -tags e2e ./e2e/...before committing. This project requires strict adherence to linting rules and 100% passing tests (including E2E tests which require tmux).
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.
- yesterday First seen · 23 lines · 300 tokens per session scan A 1322a4ce1f4d
sloop AGENTS.md is an instructions file published in the GitHub repository stroops/sloop (5 stars, last pushed 10d ago), licensed MIT. It adds 300 tokens to every session, about $0.0015 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
agent-skills AGENTS.md
Instructions for addyosmani/agent-skills, covering agents.md, repository overview, opencode integration, core rules and intent → skill mapping.
gortex CLAUDE.md
Instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
peon-ping GEMINI.md
Instructions for PeonPing/peon-ping, covering gemini.md - peon-ping, project overview, main technologies, architecture and building and running.
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.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.