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/30-harbor-format)<a href="https://agentmods.dev/rules/xclaw-bot/benchmark-task-authoring/30-harbor-format"><img src="https://agentmods.dev/badge/rules/xclaw-bot/benchmark-task-authoring/30-harbor-format/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/30-harbor-format"><img src="https://agentmods.dev/badge/rules/xclaw-bot/benchmark-task-authoring/30-harbor-format.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 | $0.01115 | $0.01115 |
| Opus 5.5 | $0.00446 | $0.00446 |
| Sonnet 5.5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade C, and why
30-harbor-format scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- apt: don't pin versions; `apt-get update` before install; `rm -rf How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Harbor/TB2 mechanical format: file layout, task.toml schema, Dockerfile rules, base images, timeouts, preflight. Auto-attaches to task files. globs: /task/ alwaysApply: false
Harbor format — the mechanical gate
Per-repo references/ files (rubric, diversity-taxonomy.toml,
check-base-image.sh) are authoritative and override anything here.
Layout
task/
instruction.md # the only thing the agent sees at runtime (HUMAN-WRITTEN)
task.toml # manifest
environment/
Dockerfile # ONE image, for both the agent run and the verifier
data/ # inputs copied in; NEVER ground truth
solution/
solve.sh # mounted at /solution, runs the reference (HUMAN-WRITTEN)
tests/
test.sh # verifier entry point; installs NOTHING
test_outputs.py # pytest assertions
expected/ # ground truth — overlaid at /tests only at verify time
Canonical TB2 uses a single image. There is no tests/Dockerfile and
[verifier] environment_mode stays unset.
task.toml
artifacts = [...]at top level, above the first[section]. Every agent-produced path the tests read must be declared.[task] name = "<program>/<kebab-name>"— inside the[task]table,org/nameformat, name part ≤3 words. A root-leveltask = "..."string makes Harbor resolve zero tasks and abort.[metadata]:category/subcategoryare pre-seeded, do not edit.task_objective[]andartifact_type[]are closed sets fromdiversity-taxonomy.toml.expert_time_estimate_hoursnon-zero and plausible. The three explanation fields must be congruent with the actual files, andverification_explanationmust justify the calibration of every tolerance.- Timeouts: agent
timeout_sec≤ 3600 (project-wide hard ceiling). Long enough that the model can finish — the challenge is correctness, not finishing in time. All five trials timing out means the timeout is too low, not the task too hard. - No invented fields; extras are silently ignored and create false impressions.
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 · 101 lines · 1,115 tokens per session scan C d080ba7155ff
30-harbor-format is a cursor rule published in the GitHub repository Xclaw-bot/benchmark-task-authoring (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,115 tokens to every session, about $0.0045 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).