finalise

A checklist for finishing code changes in a project. It requires running tests, checking code quality, and updating user and agent documentation when features change.

In plain words
What is it for?
Use it after making changes to run `mise test`, run Trunk checks, fix reported issues, and update README.md, CLAUDE.md, and related documentation.
Why use it?
It reduces the chance of handing over untested code, unresolved style problems, or documentation that no longer matches the project.

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/synmux/myriad/finalise
Clone the repo
git clone --depth 1 https://github.com/synmux/myriad
Per session 492 This file is loaded in full into every session.
When invoked 492 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 $0.00492 $0.00492
Opus 5 $0.00246 $0.00246
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash 1cf378f22c6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finalise 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.

configuration/cursor/rules/finalise.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Standard Finalization Procedure

This document outlines the standard procedure to follow after making any changes to the codebase.

Testing

  • Run the test suite to ensure all tests pass
    mise test
    
  • If tests fail, fix the issues by either:
    • Updating the code to match the test expectations
    • Updating the tests to match the new code behavior (if the changes were intentional)
  • Remember that the codebase requires Python 3.13+

Code Quality Checks

  • Run Trunk checks to identify and fix issues:
    trunk check -a --show-existing
    
  • Use the --show-existing flag to see all issues, including those that might be ignored by default
  • For targeted checks on specific files:
    trunk check --show-existing FILENAME
    
  • Fix issues using appropriate methods:
    • For formatting issues: trunk fmt FILENAME or trunk fmt -a
    • For linting issues: attempt fix with trunk check --fix FILENAME or trunk check --fix -a

Documentation Updates

After any feature changes or additions, update the following documentation files:

  1. README.md: User-facing documentation with usage examples
  2. CLAUDE.md: Detailed information for AI assistants to understand the codebase
  3. PROMPT.md: Analysis of the implementation and prompt guidance

Ensure that all three files remain in sync and provide accurate information about the project structure, features, and usage.

Sample Directory Management

The sample directory is used for testing purposes and can be reset to its original state using:

mise reset

When making changes to the sample files:

  1. Update the .sample-source directory first
  2. Then run the reset script to propagate those changes to the sample directory
  3. This ensures that users can easily reset to a clean state for testing

Final Verification

Before considering a change complete:

  1. Verify all tests pass
  2. Confirm all Trunk checks pass
  3. Ensure documentation is updated
  4. Check that the sample files are working as expected
  5. Manually test the affected functionality

Read the full file on GitHub · 70 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 · 70 lines · 492 tokens per session scan A 1cf378f22c6a

Subscribe to this mod's changes

finalise is a cursor rule published in the GitHub repository synmux/myriad (2 stars, last pushed 2d ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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.