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 jamesgray-ai/handsonai-plugins --skill writing-workflow-sopsgit clone --depth 1 https://github.com/jamesgray-ai/handsonai-pluginsWrote 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/jamesgray-ai/handsonai-plugins/writing-workflow-sops)<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/writing-workflow-sops"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/writing-workflow-sops/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/jamesgray-ai/handsonai-plugins/writing-workflow-sops"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/writing-workflow-sops.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 | $0.00128 | $0.03130 |
| Opus 5.5 | $0.00051 | $0.01252 |
| Sonnet 5.5 | $0.00026 | $0.00626 |
| Haiku 4.5 | $0.00013 | $0.00313 |
Grade A, and why
writing-workflow-sops 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Workflow SOPs
Write SOP documentation for workflows and save it as Markdown, recording the SOP path in the workflow's Workflow node where there's a registry. External trackers are out of scope.
Registry entry: the workflow's registry entry is its Workflow concept node in the registry bundle (
registry/in the working folder: the workspace on Claude Code and Codex; the folder the user selected on Claude desktop;ai-workspace/registry/, or the user's own working folder, in the user's drive on the web and in Microsoft 365, written through the connection) — seeindexing-registry/references/registry-bundle.md(in this plugin) for resolution, write rules, and your fields. With noregistry/SCHEMA.md, write no registry entry: save the SOP anyway. When the user came on their own (not from the test skill's offer), mention once that thescaffolding-registryskill sets a registry up.
Arriving from the test skill. For a team workflow, the test skill offers an SOP at go-live (and at a re-check where someone on the team is stuck), tells the user where it will be saved, and on a yes runs this skill. The user has already agreed and heard the location, so don't ask where SOPs live, and don't ask the user to confirm the execution mode or autonomy level: the Design Plan and the Workflow node settle both. Read the workflow's files (step 1), draft the SOP, show it, and save it as
[workflow-slug]-sop.mdin the workflow's folder in the framework folder (step 5) once the user is happy with it. Never save it in the workflow's own place, where the workflow runs.From Test, the SOP the user sees and saves uses only plain words. Keep
execution_modeandautonomy_levelin its frontmatter, but put no taxonomy label in the body: leave out step 4's**Execution Model:** <Mode> + <Level>line and use "How it runs" as the Execution Pattern section's label, never**<Mode> + <Level>**; never write "Augmented", "Automated", "autonomy", "deterministic" or "guided", a requirement or task ID, or a framework step number. Give no time estimates, for a Manual SOP either. Skip step 6 (no SOP link on the Workflow node and no registry refresh: the framework's node links don't include one). When it's saved, say so in one line and hand back: the test skill carries on with its next go-live step.
What ships with it
1 file 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.
- 4d ago Changed · +20 lines · +23 tokens per session 7bf2f199f30c
- 26d ago Changed d35f7040279e
- 1mo ago Changed · -1 lines 2b0e492fd5c1
- 1mo ago Changed b82a7f128e7d
- 2mo ago First seen · 144 lines · 105 tokens per session scan A c96f9beef295
writing-workflow-sops is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 3,130 once invoked, about $0.0005 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.
writing-workflow-sops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-workflow-sopsjamesgray-ai/handsonai-plugins | Skill | 8 | yesterday | MIT | A | 128 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |