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/TashanGKD/Tashan-TopicLabWrote 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/tashangkd/tashan-topiclab/backend-conventions)<a href="https://agentmods.dev/rules/tashangkd/tashan-topiclab/backend-conventions"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-topiclab/backend-conventions/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/tashangkd/tashan-topiclab/backend-conventions"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-topiclab/backend-conventions.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 | $0.00000 | $0.00486 |
| Opus 5.5 | $0.00000 | $0.00194 |
| Sonnet 5.5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
backend-conventions 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 2mo 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.
What it actually says
Backend Conventions
When working on the backend submodule (backend/), follow these conventions.
1. Documentation Location
- All backend-related docs live in
backend/docs/, not in the parent repodocs/. - Add new docs under
backend/docs/and updatebackend/docs/README.mdindex.
2. Documentation Language
- All docs in English except the main Chinese README (
backend/README.md). backend/README.en.mdis the English README.
3. Doc Filenames
- Use kebab-case for all files under
backend/docs/:- ✅
assignable-skills-flow.md,import-skill-repo.md,skills-submodule-guide.md - ❌
ASSIGNABLE_SKILLS_FLOW.md,ImportSkillRepo.md
- ✅
4. README Updates
- When adding or changing docs, update:
backend/README.md(Chinese) — 文档 sectionbackend/README.en.md— Documentation sectionbackend/docs/README.md— Document index table
5. Skills Submodule & Assignable Skills
- Add/modify skill libraries: See
backend/.cursor/skills/skills-submodule-guide/SKILL.mdorbackend/docs/skills-submodule-guide.md. - Meta architecture: Main
meta.json= sources registry only; each source has{source}/meta.jsonwithskills_dir, categories + skills. No symlinks; runtime resolves to_submodules/{source}/{skills_dir}/.... - Import script: From backend root:
./scripts/import_skill_repo.sh <url> [source]. When backend is a submodule, run from repo root:./backend/scripts/import_skill_repo.sh.
6. Path Conventions
- In backend docs and Cursor skills, use paths relative to backend root:
libs/assignable_skills/,scripts/import_skill_repo.sh,docs/
- When backend is used as submodule, parent docs may reference
backend/docs/....
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.
- 2mo ago First seen · 45 lines · 0 tokens per session scan A 7ed776cc4dd7
backend-conventions is a cursor rule published in the GitHub repository TashanGKD/Tashan-TopicLab (6 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 486 tokens. 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
protocol-conformance
A protocol drift check for keeping server-sent events and the desktop interface in agreement. It compares real event sequences with expected results and requires every event type to be handled.
api
A set of rules for building web APIs, including URL structure, request and response names, authentication, permissions, errors, and generated TypeScript types.
jelou-integration
Jelou webhook and WhatsApp messaging constraints.
backend-python
Python and FastAPI standards for the backend.
python
Python best practices and patterns for modern software development with Flask and SQLite.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.