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 anhnguyen0905/codex-mcp --skill sop-authoringgit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/sop-authoring)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/sop-authoring"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/sop-authoring/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/anhnguyen0905/codex-mcp/sop-authoring"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/sop-authoring.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 | $0.00103 | $0.01344 |
| Opus 5 | $0.00051 | $0.00672 |
| Sonnet 5 | $0.00021 | $0.00269 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
sop-authoring 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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOP Authoring (procedures a new hire can execute unaided)
The executable-SOP contract
An SOP is executable when a competent newcomer with the stated access completes it correctly without asking anyone. That needs nine elements:
Title the outcome as a task ("Refund a duplicate charge")
Trigger the exact event or condition that starts this procedure
Prerequisites access, permissions, tools, credentials, inputs, approvals needed BEFORE step 1
Steps numbered, ONE action each, imperative, with the exact UI path or command
Expected result per step: what the reader should see if it worked
Decision points explicit branches — "If X → go to 7. If Y → go to 12."
Definition of done the observable end state, plus what to record and where
Escalation who to contact, on which channel, within what time, when a step fails
Owner + dates named owner (role and person), version, last reviewed, next review date
Missing any one turns the document into a reminder for people who already know the process.
SOP vs runbook vs policy
Policy WHAT must and must not happen, and why — the rule. No steps. Changes rarely.
SOP HOW a recurring, planned task is performed correctly and repeatably.
Runbook HOW to respond to a failure or incident — diagnosis-first, branch-heavy, written for
pressure: symptoms, checks, mitigations, rollback, comms.
Do not blend them: a policy stuffed with clicks goes stale on the next UI change, and an SOP that argues rationale buries its own steps. Cross-reference instead.
Write for the least experienced reader
Assume no tribal knowledge. Expand every acronym on first use. Name the exact menu, button, table, queue or environment — never "the usual dashboard". Give the literal command with placeholders marked and the source of real values named. State what NOT to do wherever a plausible wrong action is destructive. Never write "obviously", "simply" or "just".
Weak: "Verify the payment went through in the admin panel and update the ticket."
Strong: 4. Open Admin → Payments → search the charge ID from step 2.
Expected: status reads SETTLED and the amount matches the ticket.
If PENDING, wait 10 minutes and repeat step 4 once.
If still PENDING, escalate (see Escalation) — do NOT issue a second refund.
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.
- 12d ago First seen · 105 lines · 103 tokens per session scan A 39019772f9c9
sop-authoring is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 1,344 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…