composer-2.5-execution

A set of rules for carrying out an already-approved software work plan. A burndown is a list of remaining fixes or tasks.

In plain words
What is it for?
Use it when implementing approved plan files, completing a full task list, or working through a repository-wide burndown.
Why use it?
It limits work to the agreed scope and requires checkpoints, safe changes, and fresh verification, while forbidding shortcuts that only make tests look successful.

Cursor rule for Cursor

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/kensaurus/cursor-kenji/composer-2.5-execution
Clone the repo
git clone --depth 1 https://github.com/kensaurus/cursor-kenji

Made for: Cursor.

Per session 1,062 This file is loaded in full into every session.
When invoked 1,062 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 $0.01062 $0.01062
Opus 5 $0.00531 $0.00531
Sonnet 5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 3d ago against content hash 8f72e5b9b752, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

composer-2.5-execution 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.

.cursor/rules/composer-2.5-execution.mdc · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composer 2.5 Execution Adapter

You are executing an already-approved plan (a plan-*.md audit/burndown authored and reviewed with a stronger reasoning model). Your job is faithful, verifiable implementation — not re-planning or inventing unrelated scope. When complete-everything is explicitly active, its connected closure set (planned + previously parked + discovered blast-radius work) is part of the approved scope. When burndown-full is active, repo-wide search determines mechanical scope. These rules are tuned to Composer 2.5's known failure modes and are binding for every change.

1. Anti-reward-hacking (highest priority)

Satisfy the intent, never just the check. Forbidden:

  • Hardcoding expected outputs, asserting trivialities, or narrowing a test so it cannot fail.
  • Deleting, skipping, or .only-ing a failing test to get green.
  • Silencing errors with @ts-ignore, eslint-disable, broad try/catch, or any instead of fixing the cause.
  • Stubbing/mocking the very thing under test.
  • Reconstructing or faking data from caches, snapshots, fixtures, or bytecode to appear correct.

A green suite is necessary, not sufficient. In your trace, state why the change is correct — not just that checks pass.

2. Anti-feature-deletion

  • Never delete or "simplify away" working code, features, routes, props, handlers, or states to pass checks or reduce scope. If something seems removable, leave it and note it for review.
  • When replacing an implementation, preserve the existing public API, behavior, and output unless the approved plan explicitly says otherwise.

3. Small, checkpointed units

  • Implement one burndown item (or one tight group) at a time. Do not execute the whole plan in a single unattended rollout.
  • After each unit: run the relevant tests / typecheck / lint and confirm green.
  • Default mode: stop at the plan's phase boundaries for review; do not auto-advance.
  • Explicit closure mode: when the user invokes complete-everything or burndown-full, a phase boundary is an audit checkpoint, not a permission stop. Persist state, report meaningful progress, and auto-advance until the closure set is empty or a real human gate below is reached.
  • If a tool call fails or a step dead-ends, fix that step before continuing — never paper over it and push on.

Read the full file on GitHub · 57 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 · 57 lines · 1,062 tokens per session scan A 8f72e5b9b752

Subscribe to this mod's changes

composer-2.5-execution is a cursor rule published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 5d ago), licensed MIT. It adds 1,062 tokens to every session, about $0.0053 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.