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/parzival1l/AltruWrote 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/parzival1l/altru/core)<a href="https://agentmods.dev/rules/parzival1l/altru/core"><img src="https://agentmods.dev/badge/rules/parzival1l/altru/core/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/parzival1l/altru/core"><img src="https://agentmods.dev/badge/rules/parzival1l/altru/core.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 | $0.00779 | $0.00779 |
| Opus 5.5 | $0.00312 | $0.00312 |
| Sonnet 5.5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
core 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Altru — Core Rules
Stack Conventions
Align all implementation with docs/architecture.md. Update that file as the stack is decided.
- Frontend: TBD — update
docs/architecture.mdwhen confirmed. - Backend: TBD — update
docs/architecture.mdwhen confirmed. - Infra: TBD — update
docs/architecture.mdwhen confirmed.
Architecture Update Rule (non-negotiable)
Whenever any service, data flow, API contract, or component changes:
- Update
docs/architecture.mdbefore or in the same commit as the code change. - If
docs/architecture.mdand the implementation disagree, the code is wrong — fix one or the other; never leave them out of sync. - If you are adding a new service, changing an API shape, or altering auth/data flows, update the Mermaid diagram in
docs/architecture.md.
Test-Driven Development (Mandatory for New Features)
Non-negotiable: Do not merge or ship new feature behaviour without Red → Green → Refactor TDD.
Cycle
- Red — Write a failing automated test that defines the required behaviour. Run it and confirm it fails.
- Green — Write the minimum code that makes the test pass. No extras.
- Refactor — Improve structure and remove duplication. All tests must stay green.
Defaults by Layer
- Backend: Use the project's test runner (e.g.
pytestfor Python,jest/vitestfor Node). Mock external services. Tests live inbackend/tests/. - Frontend: Use
Vitest+@testing-library/react(or the framework equivalent) for component behaviour. Tests co-located or infrontend/src/__tests__/.
Exceptions (must be noted inline)
- Pure documentation,
README,.gitignore, trivial config with no new testable behaviour may skip tests. Note the exception. - Do not skip tests for: API handlers, meaningful business logic, auth flows, or non-trivial UI logic.
Feature Tracking
- Update feature-process.md only when a feature's phase status changes meaningfully (shipped, blocked, new phase added).
- Keep it short. Use docs/ACTIVITY.md for session-level detail.
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 First seen · 88 lines · 779 tokens per session scan A 874dd3b90fda
core is a cursor rule published in the GitHub repository parzival1l/Altru (2 stars, last pushed 5mo ago), licensed MIT. It adds 779 tokens to every session, about $0.0031 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 2026-08-31.
Other cursor rules, from other repositories
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
common-testing
Testing requirements: 80% coverage, TDD workflow.
testing_rules
A testing guide covering TDD, where tests are written before code, and BDD, where expected behavior is described in Given-When-Then form.
tdd
Test-driven development — red-green-refactor cycle.
testing-standards
testing guidelines and expectations.