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 skills add 0xrafasec/ai-workflow --skill featuregit clone --depth 1 https://github.com/0xrafasec/ai-workflowWrote 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/0xrafasec/ai-workflow/feature)<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/feature"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/feature/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/0xrafasec/ai-workflow/feature"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 142 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00111 | $0.03629 |
| Opus 5.5 | $0.00044 | $0.01452 |
| Sonnet 5.5 | $0.00022 | $0.00726 |
| Haiku 4.5 | $0.00011 | $0.00363 |
Grade A, and why
feature 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 1mo 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement the feature described in $ARGUMENTS.
Parse arguments
/feature <name>→ resolve todocs/specs/NNN_<name>.md(ordocs/specs/NNN_<name>/for a sliced spec) by matching the suffix after the prefix. Specs carry a roadmap-phase-alignedNNNprefix — see/specfor the numbering rules. If multiple specs match, ask which./feature <path>.md→ use explicit path/feature #<N>→ fetch the GitHub issue#<N>viagh issue view <N>(or the GitHub MCP), extract the title and body, then resolve the spec by scanningdocs/specs/for a file whoseIssue: #<N>field matches. If found, proceed with that spec. If not found, treat the issue title/body as the feature description and ask (via AskUserQuestion) whether to create a spec first or build inline.--commit— after the feature is complete and verified, auto-commit without presenting a plan for approval. Apply the same grouping logic from/commitbut skip step 5 (plan presentation). Output only thegit log --oneline -<N>lines for the new commits. No other output.--pr— implies--commit: auto-commit (as above), then immediately open a PR without presenting a draft for approval. Apply the same PR logic from/prbut skip step 7 (draft presentation). Output only thegit log --oneline -<N>lines and the PR URL. No other output.
If the spec doesn't exist, use AskUserQuestion to ask whether to create one via /spec <name> first or build without a spec (they describe the feature inline). For bugfixes, use /fix instead.
Asking the user questions. Whenever this skill needs a decision from the user mid-flight (missing spec, slice-size override, split shape, ambiguous metadata, etc.), use the AskUserQuestion tool — never plain free-text prompts. Phrase the question clearly, lead with your recommendation as the first option labelled "(Recommended)", and keep options mutually exclusive. Free-text follow-up is always available to the user via the auto-injected "Other" choice, so don't pad with a custom-input option.
If the spec lives under docs/specs/NNN_<feature>/ (sliced spec, per /spec's trunk-based slicing), /feature implements one slice at a time. The argument must point to a specific slice file (docs/specs/NNN_<feature>/MMM_<slice>.md), never the index README.md.
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.
- 1mo ago First seen · 155 lines · 111 tokens per session scan A 410e3ea5f894
feature is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 3,629 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…