big-work-plan-review

A review rule for large, stateful, or concurrent software work. Stateful means the system keeps information over time, while concurrent means several operations can happen at once.

In plain words
What is it for?
Use it before building new systems, pipelines, background services, or other work where multiple writers, timing, or long-lived state matter.
Why use it?
It exposes design flaws before implementation, when problems such as data loss, ordering errors, or blocked processing are cheaper to fix.

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/andr-ca/agentharness/big-work-plan-review
Clone the repo
git clone --depth 1 https://github.com/andr-ca/agentharness

Made for: Cursor.

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,531 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 $0.00075 $0.01531
Opus 5 $0.00037 $0.00766
Sonnet 5 $0.00015 $0.00306
Haiku 4.5 $0.00007 $0.00153

Measured 2d ago against content hash 779efd7fa512, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

big-work-plan-review 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.

.cursor/rules/big-work-plan-review.mdc · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Big-Work Adversarial Plan Review

Ported from a workflow validated on a real design (an ntfy ingestion + persona memory pipeline) that went from roughly 3.5/10 to roughly 8.5/10 across 4 review rounds — each round finding genuine production-breaking defects a single author missed: processed-before-persisted data loss, an LLM call blocking a shared stream thread, mutable-JSONL status corruption, an answer-handling path that let contradiction answers poison an importance-rule store, and free-text LLM writes into what should have been a structured graph.

This is a from-description port. It was written from a GitHub issue proposal, not from the original Cursor-format draft it references (~/.cursor/skills/big-work-plan-review/SKILL.md, on the proposing operator's own machine) — that draft was unreachable from the session that built this file. Reconcile against the original draft if it surfaces later; treat this version as functionally complete in the meantime, not as a placeholder.

When to use this

Big, stateful, or concurrent work: new systems, pipelines, daemons, anything with multiple writers, ordering dependencies, or state that outlives a single request. The cost of a design mistake here is a production incident, not a failed test.

When NOT to use this: a scoped bug fix with one clear resolution, a single-file change, or anything requirements-clarification already covers by itself. Running a two-reviewer adversarial loop on a small change is pure overhead — match the ceremony to the blast radius.

The loop

  1. Research verified facts, not assumptions. Probe the live systems this design touches — actual schemas, actual message shapes, actual failure behavior — before writing a line of the plan. Record findings in a "Current state (verified)" section so a reviewer can tell what you checked from what you assumed.

  2. Write the plan. One doc in docs/plans/, with these sections at minimum:

    • Goal
    • Current state (verified)
    • Architecture
    • Exact schemas / DDL / message contracts
    • Module contracts (inputs, outputs, invariants each module owns)
    • Failure-modes table (what breaks, how it's detected, what happens next)
    • Testing approach
    • Out of scope

Read the full file on GitHub · 136 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 · 136 lines · 75 tokens per session scan A 779efd7fa512

Subscribe to this mod's changes

big-work-plan-review is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,531 once invoked, about $0.0004 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.