A tool for viewing or changing review and agent-dispatch effort settings in a Codex session. It supports separate tiers for Claude review, Codex review, Codex dispatch, and Codex defaults.

It helps check settings, set documented effort levels or backends, validate configuration, and identify backups or errors when changes cannot be applied.

It makes the current review and dispatch configuration visible and provides a controlled way to update it.

sop-tier — Skill for Claude Code by Gnayj

Install

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.

Any agent

npx skills add Gnayj/claude-code-sop --skill sop-tier

Clone the repo

git clone --depth 1 https://github.com/Gnayj/claude-code-sop

Made for: Claude Code.

Or install ccsop, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 3 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gnayj/claude-code-sop/sop-tier.svg)](https://agentmods.dev/skills/gnayj/claude-code-sop/sop-tier)

Your own site

<a href="https://agentmods.dev/skills/gnayj/claude-code-sop/sop-tier"><img src="https://agentmods.dev/badge/skills/gnayj/claude-code-sop/sop-tier.svg" alt="Measured on agentmods" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 518 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00028	$0.00518
Opus 5	$0.00014	$0.00259
Sonnet 5	$0.00006	$0.00104
Haiku 4.5	$0.00003	$0.00052

Measured yesterday against content hash c6938c809ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sop-tier 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 yesterday.

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.

templates/codex-scaffold/skills/sop-tier/SKILL.md · 33 lines

What it actually says

SOP Tier

Read references/contract.md.

Empty arguments or implicit activation are read-only: call ccsop_configure action=status.
Legal schema-1 scopes are claude-review, codex-review, codex-dispatch, and codex-default. Schema 2 additionally exposes claude-implement.
An explicit mutation first reads status and requires contract_version=2 / observed_schema=1|2, then calls ccsop_configure action=set-tier with the status sha and only the selected scope's documented fields.
If status reports config_valid=false, display its validation error and raw tiers. A legal set may repair the selected target keys only when the resulting whole config validates; unrelated errors fail with zero writes. Point to /sop-update or a verified .ccsop/backups/config/<sha256>.toml preimage, never a manual-edit fallback.
Codex effort: ""|minimal|low|medium|high|xhigh|max|ultra; max and ultra are model-dependent and the Codex host validates the effective model/effort pair at invocation. Claude review effort: ""|low|medium|high|xhigh|max; Claude review backend is api|cli.
claude-implement requires schema 2 plus a live claude_implement tool. It accepts model/effort and shrink-only timeout/output/per-design/daily budget caps. Never send backend, cli_path, version override, validation paths/commands/globs, advisory apply, or enabled: those are operator-only. A requested limit above min(on-disk current, compiled maximum) is a zero-write error.
codex-dispatch controls codex_implement, not the current host session. Use built-in /model for the current Codex session.
Reject every other scope. On schema 1, fail claude-implement with /sop-update remediation while preserving the Phase 1 scopes. On a missing/old/unrestarted tool, make zero writes, give /mcp reconnect guidance, and never fall back to manual TOML/shell editing.

Files

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.

references/contract.md 1.9 KB

Changes

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.

yesterday Changed c6938c809ff5
6d ago First seen · 33 lines · 28 tokens per session scan A 7736282536b2

Subscribe to this mod's changes

sop-tier is a skill published in the GitHub repository Gnayj/claude-code-sop (2 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 518 once invoked, about $0.0001 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.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens