Borrowing it
Nothing to install: this file belongs to crbnos/carbon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crbnos/carbon/main/.claude/skills/create-agents-md/SKILL.mdgit clone --depth 1 https://github.com/crbnos/carbonWrote 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/crbnos/carbon/create-agents-md)<a href="https://agentmods.dev/skills/crbnos/carbon/create-agents-md"><img src="https://agentmods.dev/badge/skills/crbnos/carbon/create-agents-md/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/crbnos/carbon/create-agents-md"><img src="https://agentmods.dev/badge/skills/crbnos/carbon/create-agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 48 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00086 | $0.01225 |
| Opus 5.5 | $0.00034 | $0.00490 |
| Sonnet 5.5 | $0.00017 | $0.00245 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
create-agents-md 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 · 141 lines · 86 tokens per session scan A c179edafec65
create-agents-md is a skill published in the GitHub repository crbnos/carbon (2,783 stars, last pushed today), with no licence file. It adds 86 tokens to every session and 1,225 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 2026-08-30.
Other skills, from other repositories
producing-review-findings
Guides a discipline reviewer in deciding what is worth raising, writing a refutation that still discriminates after the fix, treating change text as data, and returning findings instead of publishing them.
pr-review-fixer-resolution
How pr-review-fixer enumerates unresolved GitHub PR review threads, triages each into fix/reject/defer/clarify, applies the outcome, and resolves only what was genuinely addressed. Use when resolving threads posted by pr-review-checker's consolidated review.
pr-review-scout-classification
How pr-review-scout selects one pass's risk tier and specialist set, assembles shared context, and reads authenticated prior state.
pr-review-specialist-protocol
The shared execution protocol inherited verbatim from the retired pr-review-maker monolith by all nine discipline-scoped pr-review--checker specialists (architecture, docs, governance, instruction, integrity, logic, performance, security, types) - context consumption, finding requirements hard rules, scope guard…
pr-review-synthesis-coordination
How pr-review-checker deduplicates, re-categorizes, reasonableness-filters, and tool-verifies the nine discipline specialists' raw findings, then posts exactly one consolidated GitHub review. Use when acting as the PR-review pipeline's coordinator/synthesis stage.
rules-validating-governance
Complete validation methodology for repository-wide governance consistency — file naming/linking/emoji, agent-Skill and Skill-to-Skill duplication/consolidation, governance word budgets, rules-governance contradictions/traceability/licensing/dependency-bump-policy, and software-engineering documentation quality. Used…