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.
npx agentmods add rules/andr-ca/agentharness/big-work-plan-reviewgit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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.
| Model | Per session | Once 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 |
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.
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
-
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.
-
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
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.
- 2d ago First seen · 136 lines · 75 tokens per session scan A 779efd7fa512
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.
Other cursor rules, from other repositories
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
cursorrules
This repo has a GraphPilot structural code-graph available via MCP. Use it before grep on structural questions.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.