agentrisk AGENTS.md

Contribution instructions for AgentRisk, a project that evaluates whether financial actions should be allowed or blocked under defined policies.

In plain words
What is it for?
Use them when changing AgentRisk to run its tests, linting, type checks, and example program while preserving restrictions on network access, credentials, policy handling, and user-facing messages.
Why use it?
They define the project’s required setup, verification commands, security boundaries, and fail-closed behavior for contributors.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/trycoin-ai/agentrisk/agents-md
Clone the repo
git clone --depth 1 https://github.com/trycoin-ai/agentrisk

Made for: Codex, OpenCode.

Per session 710 This file is loaded in full into every session.
When invoked 710 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00710 $0.00710
Opus 5 $0.00355 $0.00355
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 2d ago against content hash 549e1215763a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentrisk 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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on AgentRisk

Instructions for coding agents (and humans) contributing to this repository.

Setup and verification

python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

pytest                       # full suite; must be green
ruff check .                 # lint; must be clean
mypy                         # types; must be clean
python examples/agent_loop.py  # end-to-end smoke test

Rules that are not negotiable

  1. The core stays pure. Nothing under src/agentrisk/ may make network calls, call an LLM, or read credentials. Mutable file I/O is limited to the policy file, its history, and the audit log, all via store.py and audit.py. The one other read is the bundled classification data in src/agentrisk/data/, loaded read-only through importlib.resources.
  2. Fail closed. A missing policy or invalid input must produce BLOCK, never a pass. Do not weaken this.
  3. Exits are never trapped. Selling or closing a position must never be blocked by a concentration or asset-class rule.
  4. All user-facing wording lives in messages.py. Never use the words "safe", "approved", or "recommended" in output. Always attribute limits to the user ("your 25% limit").
  5. Determinism. Same inputs must produce byte-identical output. No calls to datetime.now() inside check logic without the now parameter plumbed through.

Golden fixtures

Any intentional change to check math or message wording requires regenerating the golden snapshots and reviewing the diff:

AGENTRISK_REGEN=1 pytest tests/test_golden.py
git diff tests/golden

Unexplained golden diffs mean you broke something.

Layout

  • src/agentrisk/models.py: pydantic schemas, strict validation, Decimal money.
  • src/agentrisk/check.py: trade simulation, aggregation, and the check_trade_risk entry point.
  • src/agentrisk/checks.py: the risk-check catalog, one function per rule.
  • src/agentrisk/overrides.py: one-time override tiering and application.
  • src/agentrisk/analyze.py: portfolio report and compliance audit.
  • src/agentrisk/policy.py: policy lifecycle, diff, confirm gate, history.
  • src/agentrisk/mcp_server.py: thin MCP adapter; contains no business logic.
  • src/agentrisk/cli.py: the agentrisk command; wraps the three tools, no logic.
  • src/agentrisk/data/: classification seed data; lint in tests/test_seed_data.py.
  • skills/agentrisk/SKILL.md: the optional Agent Skill; a thin protocol, no logic.
  • .claude-plugin/ and .mcp.json: Claude Code plugin manifest, its marketplace, and the bundled MCP server registration (launched via uvx); lint in tests/test_skill.py.

Read the full file on GitHub · 67 lines

Changes

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.

  1. 2d ago First seen · 67 lines · 710 tokens per session scan A 549e1215763a

Subscribe to this mod's changes

agentrisk AGENTS.md is an instructions file published in the GitHub repository trycoin-ai/agentrisk (2 stars, last pushed 16d ago), licensed MIT. It adds 710 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories

OpenQuantum AGENTS.md

Instructions for xi-zhao/OpenQuantum, covering openquantum, 四个职责面, 扩展对象不可混用, 不变量 and 代码位置.

xi-zhao/OpenQuantum · 1,611 tokens

clawock AGENTS.md

Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.

KCNyu/clawock · 2,140 tokens

clawock CLAUDE.md

Instructions for KCNyu/clawock, covering claude.md, identity & user, required reads (every session, in order), what lives where and cron run loop (what openclaw fires).

KCNyu/clawock · 867 tokens

regulated-mcp-insurance-deployment AGENTS.md

AGENTS.md instructions for waalwalker1/regulated-mcp-insurance-deployment, covering agents.md — regulated mcp insurance reference architecture, architectural invariants, developer command interface, architecture & verification ledgers and subsystem & file ownership.

waalwalker1/regulated-mcp-insurance-deployment · 702 tokens

mcp-shopline CLAUDE.md

Instructions for asgard-ai-platform/mcp-shopline, covering claude.md, project overview, setup & running, run the mcp server directly (stdio json-rpc 2.0) and or auto-detected via .mcp.json when opened in claude code.

asgard-ai-platform/mcp-shopline · 1,400 tokens

centrapay-mcp CLAUDE.md

Claude Code instructions for CedricConday/centrapay-mcp, covering centrapay-mcp — claude code instructions, what this project is, credentials, build and test and architecture.

CedricConday/centrapay-mcp · 615 tokens