Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add animalzinc/claude-plugins/plugin install blog-style-guide-creatorWrote 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/animalzinc/claude-plugins/validate-style-guide)<a href="https://agentmods.dev/skills/animalzinc/claude-plugins/validate-style-guide"><img src="https://agentmods.dev/badge/skills/animalzinc/claude-plugins/validate-style-guide/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/animalzinc/claude-plugins/validate-style-guide"><img src="https://agentmods.dev/badge/skills/animalzinc/claude-plugins/validate-style-guide.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 | $0.00074 | $0.00615 |
| Opus 5.5 | $0.00030 | $0.00246 |
| Sonnet 5.5 | $0.00015 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
validate-style-guide 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 2d 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.
What it actually says
Validate a style guide
Checks one guide in two passes: code for the schema, then an auditor for what needs reading. Changes nothing unless the user asks.
Arguments: $ARGUMENTS
Every sgc step is python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sgc.py" <command> ..., written out in full and run as its own Bash call, never chained with ;, &&, or a pipe, so it matches the skill's permission for sgc. On Windows, py -3 in place of python3. Without Python 3.9 or later, stop and say the plugin needs it.
- The plugin's guides folder setting reads:
${user_config.guides_dir}. Runsgc brand-path <brand> --project-dir "${CLAUDE_PROJECT_DIR}", adding--guides-dir "<path>"only when that setting is an absolute path (an unset setting shows as text starting with${, which must never reach the shell), and--guide Fwhen given. Without a guide, stop and offerbuild-style-guide. - A
schema_versionof 1: report that the guide predates rule IDs, that the checks still read it, and thatbuild-style-guide <brand> --upgradeconverts it. Then audit it as it is. - Run
sgc guide validate <guide>andsgc guide parse <guide> --out <brand_dir>/builds/<YYYY-MM-DD>/rules.json. - Launch
blog-style-guide-creator:guide-auditorwithmodel: "${user_config.deep_model}"(leavemodelout when the value is empty or still reads${), giving the guide path, the parsed rules path, the validate output, and the output<brand_dir>/builds/<YYYY-MM-DD>/audit.json. - Report the schema errors and warnings, then the audit's findings grouped by type (contradiction, example conflict, vague, overlap, check mismatch, scope gap), each with the rules involved and the proposed fix. End with the counts.
- When the user asks for fixes, make them through
build-style-guide's approve-and-write steps, so the diff is shown before the guide changes.
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.
- 2d ago First seen · 22 lines · 74 tokens per session scan A 5cfefcc90ba9
validate-style-guide is a skill published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 615 once invoked, about $0.0003 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 2026-11-11.
validate-style-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| validate-style-guideanimalzinc/claude-plugins | Skill | 15 | 2d ago | MIT | A | 74 | Claude Code |
| cf-style-guideteachskillofskills-ai/ContentForge-techshu | Skill | 1 | 2mo ago | MIT | A | 178 | Claude Code |
| cf-briefteachskillofskills-ai/ContentForge-techshu | Skill | 1 | 2mo ago | MIT | A | 169 | Claude Code |
| cf-helpteachskillofskills-ai/ContentForge-techshu | Skill | 1 | 2mo ago | MIT | A | 149 | Claude Code |
| cf-publishteachskillofskills-ai/ContentForge-techshu | Skill | 1 | 2mo ago | MIT | A | 168 | Claude Code |
| cf-templateteachskillofskills-ai/ContentForge-techshu | Skill | 1 | 2mo ago | MIT | A | 160 | Claude Code |
| cf-variantsteachskillofskills-ai/ContentForge-techshu | Skill | 1 | 2mo ago | MIT | A | 162 | Claude Code |