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/briangmilnes/apas-verus/propose-new-workgit clone --depth 1 https://github.com/briangmilnes/APAS-VERUSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/briangmilnes/apas-verus/propose-new-work)<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/propose-new-work"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/propose-new-work.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.00568 |
| Opus 5 | $0.00004 | $0.00284 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
propose-new-work scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Propose New Work
When the user says "propose new work", "proposed work table", or "retable", generate a table of actionable work from the proof holes report. Write output to plans/proposed-work.md (see plans-directory rule).
Procedure
-
Run proof holes chapter by chapter on the agent's assigned chapters:
for ch in Chap02 Chap03 Chap05 Chap06 Chap11 Chap12 Chap17 Chap18 Chap19 Chap21 Chap23 Chap26 Chap27 Chap28 Chap35 Chap36 Chap37 Chap38 Chap39 Chap40 Chap41; do ~/projects/veracity/target/release/veracity-review-proof-holes -d "src/$ch/" done -
For each holed file, determine whether it has proposed work:
- Yes: non-standard assume, external_body hiding algorithmic logic, bare_impl (except iter_mut/recursive-spec-fn)
- No: accepted patterns only — PartialEq assume, Clone assume, assume_eq_clone_workaround,
assume(false); diverge()in thread join, external_body at threading boundaries, external_body at AtomicUsize (Chap12)
Do not table proposed work on assume_eq_clone_workaround.
-
List only files with proposed work. If a chapter has multiple holed files, include only those with proposed work (e.g., Chap19: ArraySeqMtEphSlice has bare_impl; ArraySeqMtEph/StEph/StPer have PartialEq only → list only ArraySeqMtEphSlice).
-
Output table format: | # | Chapter | Holed Files | Proposed Work | Cells ≤ 40 chars. Avoid the word "in" in cells (use "lacking" not "without"). Last column (Proposed Work): Keep each cell ≤ 30 chars. Use terse abbreviations (e.g. "ext_body" not "external_body", "struct out" for "struct outside verus"). If needed, move detail to a footnote below the table.
-
Skip chapters with no proposed work. Do not include rows where all holes are accepted patterns.
-
Write the table to
plans/proposed-work.md.
Permanent external_body (no proposed work)
- Chap02 HFSchedulerMtEph: threading boundary
- Chap12 Exercise12_1, Exercise12_5: AtomicUsize operations
- Chap35 OrderStatSelectMtEph/MtPer: parallel partition
- Chap38 BSTParaMtEph: threading boundary
- Chap39 BSTParaTreapMtEph: threading boundary
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.
- 6d ago First seen · 43 lines · 8 tokens per session scan A d4651bb7e6ca
propose-new-work is a cursor rule published in the GitHub repository briangmilnes/APAS-VERUS (10 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 568 once invoked, about $0.0000 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.