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 agentmods add skills/chrislamdev/hermes-core-skills/batch-skill-description-standardizationnpx skills add ChrisLamDev/hermes-core-skills --skill batch-skill-description-standardizationgit clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skillsWrote 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/chrislamdev/hermes-core-skills/batch-skill-description-standardization)<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/batch-skill-description-standardization"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/batch-skill-description-standardization.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01926 |
| Opus 5 | $0.00019 | $0.00963 |
| Sonnet 5 | $0.00008 | $0.00385 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
batch-skill-description-standardization scanned grade A 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
r = subprocess.run(['head', '-15', f], capture_output=True, text=True, timeout=5) How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Skill Description Standardization
When to Use This Skill
When you need to update descriptions across 20+ SKILL.md files with a consistent pattern (e.g. converting all to "Use when..." format).
The Problem
An agent skills directory can have 160+ SKILL.md files with inconsistent descriptions. Some describe workflow instead of triggering conditions. Some start with verbs. Some are 80+ words long. Patching them one-by-one uses 100+ tool calls and is prone to error.
The Superpowers Insight (CSO)
From superpowers' "Claude Search Optimization" analysis:
- If description summarizes workflow, the agent follows the description and SKIPS the skill body.
- Description should ONLY describe WHEN to use, NEVER WHAT the skill does.
- Format: "Use when [precise triggering condition]."
The Workflow
Step 1: Scan and classify
from hermes_tools import search_files, read_file
import re
result = search_files(pattern='SKILL.md', target='files', path='/path/to/skills', limit=200)
files = result['files']
Check each SKILL.md's description line for three problems:
- Doesn't start with "Use when" — most common
- Describes workflow (has words like "步驟", "流程", "phase", "checklist", "step 1")
- Too long (over 80 words)
Step 2: Handle the two YAML description formats
There are TWO formats for description in SKILL.md frontmatter:
Format A — Single line:
description: Some text here.
Format B — Folded multiline (uses > or >-):
description: >
Long text that spans
multiple lines in the file
but becomes one line in YAML.
CRITICAL: For Format B, you CANNOT just replace the description line. You must replace the ENTIRE block from description: to the next YAML key.
Step 3: Write the batch script
Build a Python dict mapping skill identifiers to new descriptions. Use a script with re.sub() to find and replace:
pattern = r'(description:\s*)(.+?)(?=\n(?:---|name:|version:|author:|title:|tags:|category:|metadata:|last_|created:|related|triggers|license:| )|\Z)'
replacement = f'description: {new_desc}'
new_content = re.sub(pattern, replacement, content, count=1, flags=re.DOTALL)
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.
- 5d ago First seen · 157 lines · 38 tokens per session scan A 5bd1345c8c2c
batch-skill-description-standardization is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,926 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-code-review
This is a Hermes-native code-review workflow skill.