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.
git clone --depth 1 https://github.com/autogrammar/todo2codeWrote 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/autogrammar/todo2code/new-project-standard)<a href="https://agentmods.dev/rules/autogrammar/todo2code/new-project-standard"><img src="https://agentmods.dev/badge/rules/autogrammar/todo2code/new-project-standard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/autogrammar/todo2code/new-project-standard"><img src="https://agentmods.dev/badge/rules/autogrammar/todo2code/new-project-standard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00490 | $0.00490 |
| Opus 5.5 | $0.00196 | $0.00196 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
new-project-standard 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 1mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managed standard sources
Local adoption files are authoritative. Remote links are navigation only and must not be fetched or executed at runtime.
- Local adoption manifest: .governance/manifest.json
- Local adoption lock: .governance/manifest.lock.json
- Local package map: .governance/package-manifest.json
- Canonical instructions: AGENTS template
- Host contract: agent-hosts.json
- Immutable adoption/updater: create_adoption_lock.py
new-project standard (host-agnostic)
Before writing code in this repository:
- Read
AGENTS.mdand the active ticket. Reuse anIN_PROGRESSticket only when workstream and scope match. - Otherwise run
./project/new-ticket.sh --title "..." --agent "..." --workstream "...". - Work in a dedicated worktree/branch whose name contains
ticket-NNN. Do not commit onmainor a dirty primary checkout. - Stay inside
intent.jsonallowedPaths. Commercial SSOT / offer / brand facades need the integration workstream. - Run
./scripts/install-agent-hosts.shonce per clone so.githooks/pre-commitis active. - Run
./project/governance-check.shbefore claiming done.
The pre-commit hook rejects commits that are not bound to an IN_PROGRESS ticket. Do not invent ticket numbers. Do not ask the human to approve a merge; invoke validator-agent when publication needs trusted approval.
Bounded session controls: respect the ticket's maxActiveMinutes, create a
checkpoint before a context or tool boundary, and leave a handoff then
stop after a deterministic failure instead of retrying indefinitely.
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.
- 1mo ago Changed · +19 lines · +252 tokens per session 8884003b3a44
- 1mo ago First seen · 18 lines · 238 tokens per session scan A 72699a5cb371
new-project-standard is a cursor rule published in the GitHub repository autogrammar/todo2code (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 490 tokens to every session, about $0.0020 per session on Opus 5.5. 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 2026-09-11.
Other cursor rules, from other repositories
git-conventions
See CONTRIBUTING.md → "PR & commit conventions" for PR title format, commit messages, and branch naming.
beads
This project uses Beads (bd) for issue tracking.
commit-and-push
Commit (conventional commit) files and push to the remote repository.
git
Cursor rule "git" from duongductrong/antigravity-kit, covering git conventions, commit messages, types, subject rules and examples.
check
Analyze staged git changes with archguardian before committing.
git-workflow
Git workflow: commits, branches, PRs, history management.