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/dppdppd/rpm/auditnpx skills add dppdppd/rpm --skill auditgit clone --depth 1 https://github.com/dppdppd/rpmWrote 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/dppdppd/rpm/audit)<a href="https://agentmods.dev/skills/dppdppd/rpm/audit"><img src="https://agentmods.dev/badge/skills/dppdppd/rpm/audit.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 | $0.00098 | $0.02516 |
| Opus 5 | $0.00049 | $0.01258 |
| Sonnet 5 | $0.00020 | $0.00503 |
| Haiku 4.5 | $0.00010 | $0.00252 |
Grade A, and why
audit 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 3d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit
On-demand audits. Three distinct targets, no depth menu, no recency
recommendation. Routine doc-drift is handled automatically by
/session-end — run /audit only when you have a specific
concern that warrants a deeper look.
Project Amendments
At the start of every invocation, check whether
docs/rpm/skills/audit.md exists in the consuming project. If it
does, read it and apply its contents as additional project-specific
instructions for this skill. Amendments may add audit dimensions,
require extra scans, or extend the report format. They cannot remove
or override plugin defaults — on conflict, this SKILL.md wins.
Routing
Parse $ARGUMENTS:
-
quick→ run the Quick audit below (mechanical scan.sh only, no LLM scan) -
documents(ordocs) → run the Documents audit below -
project→ run the Project audit described in project-mode.md. Read that file and follow it end-to-end — it contains the full 5-phase protocol, the analyze dimensions, and the deliverables spec. -
empty or unrecognized → print the usage block and stop:
## /audit — pick a target - `/audit quick` — mechanical scan.sh only. Git state, agent instructions size, NOT_IMPLEMENTED, broken refs, daily-log gap, session marker, spec inventory drift, log/tracker staleness. Zero LLM tokens for the scan itself. ~5sec. - `/audit documents` — scan docs + agent instructions + memory + session drift via the rpm:auditor review agent. Scored findings, codify repeat offenders. ~3min. - `/audit project` — full consultant review: code, architecture, inward + outward research, 7-dimension analysis, saved plan file. ~30min+. Routine doc-drift runs automatically at /session-end.
Target: Quick
Mechanical drift scan only — no rpm:auditor subagent, no LLM
scan, no 110-doc walk. Runs skills/session-end/scripts/scan.sh
via direct shell injection and interprets the output.
Use when you want a fast "anything broken right now?" check between session-ends, or to verify a fix landed, without committing to a full documents audit.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 256 lines · 98 tokens per session scan A 88782cd55c52
audit is a skill published in the GitHub repository dppdppd/rpm (3 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 2,516 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hf-cloud-sagemaker-production-defaults
Implement a production SageMaker endpoint with autoscaling, CloudWatch alarms, and tags. Use after the serving image and IAM role are known; use the deployment planner first when architecture is undecided.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
train-sentence-transformers
Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka. Use for sentence-transformers training tasks.
transformers-js
Run Hugging Face models in JavaScript or TypeScript with Transformers.js, WebGPU, or WASM across browser, Node.js, Bun, and Deno. Use for client-side or JS-runtime inference, not Python training.
huggingface-best
Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.