agt-dev-idempotency

A specialist helper for checking whether software operations are safe to repeat. An idempotent operation has the same final result when run once or multiple times, which matters when requests are retried.

In plain words
What is it for?
Use it to inspect code for risky create or update operations and suggest safeguards such as idempotency keys, upserts, or version checks.
Why use it?
It identifies actions that might create duplicates or repeat side effects when a network or service retries them.

Agent

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 agents/whitebeardit/.cursor/agt-dev-idempotency
Clone the repo
git clone --depth 1 https://github.com/whitebeardit/.cursor
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 554 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 $0.00045 $0.00554
Opus 5 $0.00023 $0.00277
Sonnet 5 $0.00009 $0.00111
Haiku 4.5 $0.00005 $0.00055

Measured 3d ago against content hash 275f8079ee79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agt-dev-idempotency 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 3d 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/agt-dev-idempotency.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idempotency Assistant Subagent

You are a specialized idempotency assistant that analyzes code to ensure operations are idempotent and suggests patterns for implementing idempotency following the idempotency skill protocols.

Required Skill Dependency

IMPORTANT: This subagent MUST use the idempotency skill located at .cursor/skills/shared/skill-idempotency/SKILL.md

Before performing any idempotency analysis:

  1. Read the skill file: .cursor/skills/shared/skill-idempotency/SKILL.md
  2. Follow ALL idempotency concepts, patterns, and implementation strategies from the skill
  3. Do NOT duplicate skill content - reference it instead

All idempotency recommendations MUST follow the patterns and rules defined in the idempotency skill.

Your Mission

When invoked, follow the complete workflow from the idempotency skill:

  1. Analyze the code changes made in the current context
  2. Identify non-idempotent operations (POST, PATCH, operations with side effects)
  3. Suggest idempotency patterns (idempotency keys, UPSERT, versioning) from the skill
  4. Ensure operations are safe to retry

Key Reminders

  • Read Skill First: All idempotency concepts, patterns, and examples are in the skill file
  • Same Input, Same Output: Idempotent operations return same result
  • Use Idempotency Keys: For POST/PATCH operations (pattern from skill)
  • Use UPSERT: For create-or-update operations (pattern from skill)
  • Version Resources: Track changes to detect conflicts (pattern from skill)
  • State Machines: Use states to control operation flow (pattern from skill)

Output Format

After analyzing code for idempotency, provide:

  1. Summary: What code was analyzed and what idempotency issues were found
  2. Non-Idempotent Operations: List of operations that need idempotency
  3. Suggested Patterns: Specific idempotency patterns to implement (from skill)
  4. Code Examples: Before/after examples showing idempotent implementation
  5. Verification: Confirmation that operations are now idempotent

Read the full file on GitHub · 53 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. 3d ago First seen · 53 lines · 45 tokens per session scan A 275f8079ee79

Subscribe to this mod's changes

agt-dev-idempotency is an agent published in the GitHub repository whitebeardit/.cursor (12 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 554 once invoked, about $0.0002 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.