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/ambient-code/agentready/agents-mdgit clone --depth 1 https://github.com/ambient-code/agentreadyWhat 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 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
agentready 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 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.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentReady
Assess repositories against evidence-based attributes for AI-assisted development readiness.
Commands
# Core
agentready assess <repo> # Assess repository
agentready bootstrap <repo> # Setup agent-ready infrastructure
agentready align <repo> # Automated remediation
# Development
pytest # Run tests
pytest --cov=src/agentready # With coverage
black . && isort . && ruff check . # Lint
# Local development (uses this checkout, not the installed package)
PYTHONPATH=src python -m agentready assess <repo>
Data Flow
Repository -> Scanner -> Assessors -> Findings -> Scorer -> Reporters
Scoring
Certification levels: Platinum (90+), Gold (75-89), Silver (60-74), Bronze (40-59)
Adding Assessors
- Create class inheriting
BaseAssessor(assessors/base.py) - Implement
attribute_idproperty andassess(repository)method - Register in
assessors/__init__.py:create_all_assessors() - Add tests in
tests/unit/test_assessors_*.py
Key Patterns
Proportional scoring: Use calculate_proportional_score() for partial compliance
Graceful degradation: Return "skipped" if tools missing, never crash
Finding creation:
Finding.create_pass(self.attribute, evidence="...", details="...")
Finding.create_fail(self.attribute, evidence="...", remediation="...")
Conventions
Commits: feat:, fix:, docs:, test:, refactor:, chore:
Tests: All new assessors require unit tests. Maintain >80% coverage for new code.
Linting: Run black . && isort . && ruff check . before commits
CI changes: Always run actionlint before pushing workflow changes.
Agent Guidelines
- Read before modifying: understand existing assessors first
- Follow patterns: use reference implementations (grep for
BaseAssessorsubclasses) - Test thoroughly: unit tests required for all assessors
- Backwards compatibility: schema version bump for model changes
- Rich remediation: actionable steps with tools, commands, examples
- Self-assign issues: before starting work on a GitHub issue, check if it is already assigned. If it is, warn the user and ask for confirmation before continuing. If unassigned (or the user confirms), self-assign it immediately to prevent duplicate effort from other contributors
- Keep docs/attributes.md in sync: when changing how an assessor scores (thresholds, partial credit rules, recognized paths, pass/fail conditions), update the corresponding entry in
docs/attributes.mdin the same PR
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 · 68 lines · 615 tokens per session scan A f5a5c4d96a01
agentready AGENTS.md is an instructions file published in the GitHub repository ambient-code/agentready (151 stars, last pushed 6d ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 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
skylos CLAUDE.md
Instructions for duriantaco/skylos, covering claude.md, what this repo is, install, use and skill for using skylos.
skylos AGENTS.md
Instructions for duriantaco/skylos, covering agents.md, what this repo is, use the skylos skill, work safely and common commands.
megalinter CLAUDE.md
Claude Code instructions for oxsecurity/megalinter, covering claude.md, project overview, development setup, shell commands — use rtk and key commands.
codexspec CLAUDE.md
Instructions for Zts0hg/codexspec, covering claude.md - codexspec development guide, project overview, purpose, technology stack and architecture.
anchorlaw AGENTS.md
Instructions for unknowbug/anchorlaw, covering anchorlaw 项目 agents.md（项目级常驻指令）, 〇、开始工作前（每个 session 必做）, 一、项目定位（一句话）, 二、主工作流（judge 驱动流水线，v0.11） and 三、技能与宿主入口.
codexspec AGENTS.md
Instructions for Zts0hg/codexspec, covering agents.md, codexspec, maintainer guide (developing codexspec itself) and codexspec project profile.