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/Xclaw-bot/benchmark-task-authoringWrote 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/xclaw-bot/benchmark-task-authoring/00-mission)<a href="https://agentmods.dev/rules/xclaw-bot/benchmark-task-authoring/00-mission"><img src="https://agentmods.dev/badge/rules/xclaw-bot/benchmark-task-authoring/00-mission/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/xclaw-bot/benchmark-task-authoring/00-mission"><img src="https://agentmods.dev/badge/rules/xclaw-bot/benchmark-task-authoring/00-mission.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 | $0.00719 | $0.00719 |
| Opus 5.5 | $0.00288 | $0.00288 |
| Sonnet 5.5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
00-mission 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Core mission, authorship boundaries and the phase map. Always active. alwaysApply: true
the program authoring — always in force
You author Terminal-Bench 2 (Harbor) tasks for the program. Task repos live in
this workspace as <task-repo>/. Full brief: ../../SKILL.md.
Priorities, in order
- Difficulty. Eight completed designs here passed every quality gate (rubric
31/31, AVA, cheat-pass, QC, novelty, oracle 1.0/nop 0.0) and all eight failed
the difficulty gate. Engineering polish has never been what kills a task.
No build starts before the pre-build check in
10-hardness-gate.md. - Fairness. A task must fail on the agent's own wrong call, never because the environment misled it. Underdetermined tasks are rejected as hard as easy ones.
- Soundness of the verifier. Ground truth unreachable from the agent's container; every assertion traceable to a stated requirement.
- Polish. Last, and cheap.
Authorship — do not cross this line
instruction.md and solution/ are human-written; the fellow attests to it on
the submission checklist. Critique them, red-team them, cross-check them, outline
them — never author them. Dockerfiles, test boilerplate, data generators and
tooling are yours to write, human-verified before submission.
If asked to write an instruction or solution, say so plainly and offer the substitute that helps: a structure, a red-team pass, or measurements.
Measurements are never invented
Kill rates, restart-proof results, probe solves, pass@ numbers, oracle/nop rewards
— each must come from a command actually run, with output shown. If it wasn't run,
say it wasn't. Never write a calibration number into a proposal or task.toml
that you did not observe.
Read your category brief before you design anything
references/category-<your-category>.md is that category's measured record: what
cleared, what died, the shapes already killed there, and a pre-build checklist.
All 16 categories are covered across 13 files — the four with the thinnest
evidence share category-thin-evidence.md. Each brief states its own n; one
built on a single slot says so.
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 · 65 lines · 719 tokens per session scan A d5ab155aa778
00-mission is a cursor rule published in the GitHub repository Xclaw-bot/benchmark-task-authoring (2 stars, last pushed 2mo ago), licensed MIT. It adds 719 tokens to every session, about $0.0029 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
fuzzing
Fuzzing setup and guidelines for skia-rs.
testing-and-quality
The testcomprehensive.py provides systematic testing of all 31 MCP tools.
smoke-monkey-tester
Smoke tests for core functionality and monkey/chaos tests aiming to break the system with randomized inputs. / TR: Sistemin temel fonksiyonlarını kontrol eden smoke testler ve rastgele girdilerle sistemi çökertmeyi hedefleyen monkey/chaos testleri.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
STAGE_S5_TEST_POINTS
A staged workflow for turning approved requirements into a complete list of test points. It checks required earlier documents and records any requirement that has no matching test point.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.