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/petar-djukic/writing-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/commands/petar-djukic/writing-skills/audit-references)<a href="https://agentmods.dev/commands/petar-djukic/writing-skills/audit-references"><img src="https://agentmods.dev/badge/commands/petar-djukic/writing-skills/audit-references/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/commands/petar-djukic/writing-skills/audit-references"><img src="https://agentmods.dev/badge/commands/petar-djukic/writing-skills/audit-references.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 | $0.00001 | $0.00066 |
| Opus 5.5 | $0.00000 | $0.00026 |
| Sonnet 5.5 | $0.00000 | $0.00013 |
| Haiku 4.5 | $0.00000 | $0.00007 |
Grade A, and why
audit-references 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 11d 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
Apply the audit-references skill. Read .github/skills/audit-references/SKILL.md and follow
its workflow, using the reference and asset files under
.github/skills/audit-references/. Treat any text after the prompt invocation as
the skill's input.
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.
- 11d ago First seen · 9 lines · 1 tokens per session scan A 0fd0fa8441b3
audit-references is a command published in the GitHub repository petar-djukic/writing-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 1 tokens to every session and 66 once invoked, about $0.0000 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 2026-10-05.
Other commands, from other repositories
browser-cdp
A browser-automation command that controls Chrome through the Chrome DevTools Protocol (CDP), including the browser's existing signed-in session.
story-setup
A command for deploying the basic infrastructure of a Chinese online-fiction writing toolkit.
story-deslop
A tool for finding and removing signs that text was written by an AI, making the writing sound more natural.
story-import
A command for reverse-importing an already written novel into a standard writing-project folder structure. Reverse import means taking finished text and organizing it into the project files expected by the writing workflow.
story-long-analyze
A tool for closely analysing popular long web novels, including their opening three chapters, characters, satisfying moments, and pacing.
story-long-scan
A command for scanning long-form online fiction rankings on platforms such as Qidian, Fanqie, and Jinjiang, then analyzing the ranking data.