security-flow-deterministic-gates

security-flow-deterministic-gates is a command for coding agents from griddynamics/rosetta. It costs 18 tokens per session (404 once invoked), scanned A, original, Apache-2.0.

Phase 3 Deterministic Gates of security-flow.

Command

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 commands/griddynamics/rosetta/security-flow-deterministic-gates
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta

Wrote 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.

agentmods badge for security-flow-deterministic-gates

README.md
[![agentmods](https://agentmods.dev/badge/commands/griddynamics/rosetta/security-flow-deterministic-gates.svg)](https://agentmods.dev/commands/griddynamics/rosetta/security-flow-deterministic-gates)
Your own site
<a href="https://agentmods.dev/commands/griddynamics/rosetta/security-flow-deterministic-gates"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/security-flow-deterministic-gates.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00018 $0.00404
Opus 5 $0.00009 $0.00202
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured today against content hash bbdf013e48a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-flow-deterministic-gates 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 today.

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.

plugins/core-copilot-light/commands/security-flow-deterministic-gates.md · 57 lines

What it actually says

<security_flow_deterministic_gates>

<description_and_purpose> Run approved deterministic high-severity gates before lifecycle AI analysis. </description_and_purpose>

<workflow_context> Phase 3 for development, change, PR, and pipeline reviews. </workflow_context>

<phase_steps>

  1. Select deterministic gates
  2. Run bounded commands
  3. Preserve sanitized results
  4. Choose lifecycle branch </phase_steps>

<execute_gates step="3.1" subagent="executor" role="Bounded deterministic security-gate operator" subagent_required_model="Claude Haiku 4.5, GPT-5.6 Terra, Gemini 3.7 Flash, GPT-5.6 Luna">

  1. USE SKILL subagent-directives.
  2. USE SKILL security.
  3. Run approved installed local tools only.
  4. Preserve command, version, configuration, timestamps, exit status, and sanitized output reference.
  5. Do not interpret beyond deterministic rule/severity results.
  6. Return unchanged source finding records.
  7. Update security-flow-state.md.

</execute_gates>

  • Any deterministic high+: HIGH+.
  • No deterministic high+: CLEAN.
  • Tool error or incomplete evidence: ERROR; stop and report the tool error; never call the gate clean.

<validation_checklist>

  • Every required gate ran successfully.
  • High+ records remain unchanged.
  • Clean means zero high+ and no tool failure.
  • Preserved evidence and output references contain no secret values. </validation_checklist>

</security_flow_deterministic_gates>

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. today First seen · 57 lines · 18 tokens per session scan A bbdf013e48a9

Subscribe to this mod's changes

security-flow-deterministic-gates is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 404 once invoked, about $0.0001 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 2026-09-03.