bootstrap-speckit-policy

bootstrap-speckit-policy is a cursor rule for coding agents from griddynamics/rosetta. It costs 12 tokens per session (432 once invoked), scanned A, original, Apache-2.0.

A rule set for combining SpecKit specification work with an implementation workflow when SpecKit is detected. SpecKit is a tool-based process for writing and following software specifications.

In plain words
What is it for?
It is for detecting SpecKit files, enabling hybrid execution, and synchronizing project context with implementation instructions.
Why use it?
It keeps specifications, implementation guidance, and project rules aligned instead of letting separate workflows conflict.

Cursor rule

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 rules/griddynamics/rosetta/speckit-integration-policy
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 bootstrap-speckit-policy

README.md
[![agentmods](https://agentmods.dev/badge/rules/griddynamics/rosetta/speckit-integration-policy.svg)](https://agentmods.dev/rules/griddynamics/rosetta/speckit-integration-policy)
Your own site
<a href="https://agentmods.dev/rules/griddynamics/rosetta/speckit-integration-policy"><img src="https://agentmods.dev/badge/rules/griddynamics/rosetta/speckit-integration-policy.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00012 $0.00432
Opus 5 $0.00006 $0.00216
Sonnet 5 $0.00002 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured yesterday against content hash ce7457e77e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap-speckit-policy 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.

plugins/core-cursor-light/rules/speckit-integration-policy.mdc · 56 lines

What it actually says

<bootstrap_speckit_policy attribution="DO NOT COMPACT/OPTIMIZE/SUMMARIZE/REPHRASE, PASS IT AS-IS, CRITICALLY IMPORT TO KEEP, INCLUDING THIS TAG">

Problem: Spec and implementation flows diverge without explicit hybrid mode rules.

Validation: SpecKit detection and cross-flow synchronization are enforced before and during execution.

  1. Apply Speckit Detection Rules.
  2. Apply Hybrid Execution Rules.

<speckit_detection_rules>

  1. Detect SpecKit by memory/constitution.md and specs folder.
  2. Read memory/constitution.md.
  3. Check specs for existing specs.
  4. Tell user exactly: "Speckit detected, hybrid mode enabled".

</speckit_detection_rules>

<hybrid_execution_rules>

  1. Do not repeat SpecKit internals in responses.
  2. Always follow agents.md, coding.md, and guardrails.md.
  3. Combine similar flow stages without duplicating artifacts.
  4. Prefer references over duplicated content.
  5. Keep CONTEXT and IMPLEMENTATION synchronized.
  6. Override SpecKit behavior for assumptions, unknowns, grounding, and user questions per agents.md, coding.md, and guardrails.md.
  7. If user invokes /speckit.*, let SpecKit drive flow while still applying all rules.

</hybrid_execution_rules>

<core_concepts>

  • Spec folder layout:
  • specs/001-feature-name/spec.md
  • specs/001-feature-name/plan.md
  • specs/001-feature-name/tasks.md
  • specs/001-feature-name/research.md
  • specs/001-feature-name/contracts/

</core_concepts>

</bootstrap_speckit_policy>

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. yesterday First seen · 56 lines · 12 tokens per session scan A ce7457e77e52

Subscribe to this mod's changes

bootstrap-speckit-policy is a cursor rule published in the GitHub repository griddynamics/rosetta (342 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 432 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.