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/0xrafasec/ai-workflow/specnpx skills add 0xrafasec/ai-workflow --skill specgit 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/spec)<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/spec"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/spec.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 | $0.00082 | $0.02153 |
| Opus 5 | $0.00041 | $0.01077 |
| Sonnet 5 | $0.00016 | $0.00431 |
| Haiku 4.5 | $0.00008 | $0.00215 |
Grade A, and why
spec 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a feature implementation spec for: $ARGUMENTS
Spec Numbering & Path
Every spec path starts with a zero-padded 3-digit prefix mirroring its roadmap phase number, so spec order matches roadmap order at a glance.
- Single spec:
docs/specs/NNN_<slug>.md - Sliced spec:
docs/specs/NNN_<slug>/containingREADME.md(index) andMMM_<slice>.mdfiles. The directory-vs-file distinction is how sliced specs are identified — theNNNprefix stays on the directory, never moves to the children. - Separator between prefix and slug is
_; within the slug, words are joined by-(e.g.,003_atlassian-integration.md, neveratlassian_integration.mdand never without the prefix).
Picking NNN:
- If this spec implements a task in
docs/roadmap/NNN_<phase>.md, use that sameNNN. Check the roadmap file before picking. - Multiple specs in one phase → disambiguate with letter suffixes
NNN.A_<name>.md,NNN.B_<name>.md, in task order. A lone spec in a phase has no suffix. - No roadmap yet → scan
docs/specs/and usemax(existing) + 1. Don't renumber later when a roadmap is added. - Never renumber an existing spec — commits, PRs, and issues reference specs by path.
Before writing any file, state the target path and confirm it satisfies the rules above.
Context Gathering
Read what already exists before interviewing:
- Existing docs:
docs/PRD.mdordocs/prd/,docs/ARCHITECTURE.md,docs/TECHNICAL_DESIGN_DOCUMENT.md,docs/THREAT_MODEL.md,README.md,CLAUDE.md. - Roadmap and specs directory: list
docs/roadmap/anddocs/specs/to pick the correctNNNper the rules above. - Existing spec for this feature — if the user is revising, don't start from scratch.
- Inherited project with no docs: read
README.md, explore directory structure, read key entry points, checkgit log --oneline -20, readpackage.json/Cargo.toml/pyproject.toml/ equivalent. Summarize what you learned to the user before the interview — "Here's what I understand about this project so far: ..."
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.
- 4d ago First seen · 158 lines · 82 tokens per session scan A ec6a986e30b3
spec is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,153 once invoked, about $0.0004 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.