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/strands-compose/sdk-python/agents-mdgit clone --depth 1 https://github.com/strands-compose/sdk-pythonWhat 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 | $0.00974 | $0.00974 |
| Opus 5 | $0.00487 | $0.00487 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
sdk-python 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strands-compose — Agent Instructions
This is strands-compose: a declarative multi-agent orchestration library for
strands-agents. It reads YAML
configs and returns fully wired, plain strands objects — no wrappers, no
subclasses.
Response Style
Answer with a short executive summary. Lead with the answer or decision in the first line.
- Direct question -> 1-3 sentences. Yes/no question -> start with yes or no.
- Expand only when asked for details, code, a full review, or a rationale.
- Prefer a compact table or 3-5 bullets over prose sections.
- Report the outcome, not the journey.
Do not
- No multi-section reports, headers, or background unless requested.
- No narrating what was searched, read, or what sub-agents found.
- No restating earlier turns, no recaps of prior decisions.
- No storytelling, no "what settled it" / "where I was wrong" essays when one line will do.
- No praise, filler, or hedging.
Still required
Brevity never overrides correctness. Keep these even when short:
- State uncertainty plainly, and say what was verified vs assumed.
- Correct a wrong earlier statement if it would change a decision.
- Flag risk before a destructive or hard-to-reverse action.
Read the Skill First — MANDATORY
Before touching any code, load the skill for the area you are working in. Skills are the authoritative source for the mental model, conventions, patterns, dependency rules, and file placement. Everything library-specific lives there, not here.
| Area | Skill to load |
|---|---|
Library source (src/strands_compose/) |
.kiro/skills/library-development/SKILL.md + .kiro/skills/library-development/references/project-map.md |
Library tests (tests/) |
.kiro/skills/library-testing/SKILL.md + .kiro/skills/library-testing/references/test-patterns.md |
If you work on the library source, read the library-development skill; if you
work on tests, read the library-testing skill. They describe the target
standard — follow it, not whatever pattern happened to be written before the
skill existed.
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 · 95 lines · 974 tokens per session scan A 1b9e1312d530
sdk-python AGENTS.md is an instructions file published in the GitHub repository strands-compose/sdk-python (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 974 tokens to every session, about $0.0049 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
job-search-agent AGENTS.md
Instructions for deeheber/job-search-agent, covering job search agent and conventions.
sample-agentic-chatbot-accelerator CLAUDE.md
Claude Code instructions for aws-samples/sample-agentic-chatbot-accelerator, covering claude.md, project, common commands, cdk (default) and terraform (experimental).
job-search-agent CLAUDE.md
Instructions for deeheber/job-search-agent, a project described as: An agent built with Strands deployed to Amazon Bedrock AgentCore to aid in the job hunt.
workflow AGENTS.md
Instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
langchain-aws AGENTS.md
Instructions for langchain-ai/langchain-aws, covering global development guidelines for the langchain monorepo, project architecture and context, langchain-aws structure, key components and langgraph-checkpoint-aws structure.
decapod CLAUDE.md
Instructions for DecapodLabs/decapod, covering claude.md - agent entrypoint, orientation & documentation, mandatory prompt safety gate, project context and quick start.