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.
npx skills add cxcscmu/SkillLearnBench --skill seven-char-regulated-versegit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/skills/cxcscmu/skilllearnbench/seven-char-regulated-verse)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/seven-char-regulated-verse"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/seven-char-regulated-verse/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/skills/cxcscmu/skilllearnbench/seven-char-regulated-verse"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/seven-char-regulated-verse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00935 |
| Opus 5 | $0.00017 | $0.00467 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
seven-char-regulated-verse 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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seven-Character Regulated Verse (七言律诗) Structure
Overview
The seven-character regulated verse is one of the most refined forms of classical Chinese poetry. It consists of exactly 8 lines, with each line containing 7 characters.
Basic Structure Requirements
Line Count
- Exactly 8 lines total
- Format: Title (on line 1), then lines 1-8 of the poem
Character Count
- Each line must have exactly 7 characters
- Characters are meaningful units in classical Chinese (not syllables)
Rhyme Scheme
- Lines 2, 4, 6, 8 must rhyme together
- Rhyming is based on modern Mandarin pronunciation (following modern pinyin)
- The rhymed character is typically at the end of the line
- All rhyming lines share the same final sound (same tone vowel + consonant)
Tonal Pattern (Ping Ze 平仄)
The classical regulated verse follows strict tonal patterns:
- 平 (píng) = level/even tones (1st, 2nd tones in Mandarin)
- 仄 (zè) = oblique/departing tones (3rd, 4th tones in Mandarin)
Standard Tonal Pattern for Seven-Character Lines
Most common pattern (one of two acceptable patterns):
Line 1: 仄 仄 平 平 仄 仄 平
Line 2: 平 平 仄 仄 平 平 仄 (rhyme)
Line 3: 平 平 仄 仄 平 平 仄
Line 4: 仄 仄 平 平 仄 仄 平 (rhyme)
Line 5: 仄 仄 平 平 仄 仄 平
Line 6: 平 平 仄 仄 平 平 仄 (rhyme)
Line 7: 平 平 仄 仄 平 平 仄
Line 8: 仄 仄 平 平 仄 仄 平 (rhyme)
Alternative pattern:
Line 1: 平 平 仄 仄 平 平 仄
Line 2: 仄 仄 平 平 仄 仄 平 (rhyme)
Couplet Structure
The 8 lines form 4 couplets:
- Opening couplet (lines 1-2): Introduces the theme
- Development couplet (lines 3-4): Develops the theme further
- Turning couplet (lines 5-6): Shifts perspective or deepens meaning
- Closing couplet (lines 7-8): Resolves or concludes
Content Requirements
- Each couplet should be relatively self-contained in meaning
- Lines within a couplet should relate to each other
- The poem should have a coherent overall narrative or emotional arc
- Classical imagery and allusions are preferred
Antithesis (Duiou 对偶)
Regulated verses typically feature antithetical couplets where:
- Opposite or complementary concepts are placed in parallel
- Parallel grammatical structures are used
- Creates balance and emphasis
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.
- 9d ago First seen · 94 lines · 35 tokens per session scan A 23647e678f68
seven-char-regulated-verse is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 935 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
content-creator-setup
One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.
github
GitHub API integration via HTTP tool with automatic credential injection.
idea-parking
Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.
codspeed-optimize
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…
agentsop-llm-artifact-versioning
Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is…