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 commands/gnayj/claude-code-sop/sop-updategit clone --depth 1 https://github.com/Gnayj/claude-code-sopWrote 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/commands/gnayj/claude-code-sop/sop-update)<a href="https://agentmods.dev/commands/gnayj/claude-code-sop/sop-update"><img src="https://agentmods.dev/badge/commands/gnayj/claude-code-sop/sop-update.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 | $0.00089 | $0.09084 |
| Opus 5 | $0.00044 | $0.04542 |
| Sonnet 5 | $0.00018 | $0.01817 |
| Haiku 4.5 | $0.00009 | $0.00908 |
Grade A, and why
sop-update 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 3d 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sop-update — incremental update of ccsop-owned files
This is the single-source repair loop: ccsop-owned generic files are re-materialized from the
plugin; local breakpoint/overlay files are never touched. Plugin root = ${CLAUDE_PLUGIN_ROOT};
target repo = ${CLAUDE_PROJECT_DIR}. $ARGUMENTS may contain --force, a path filter, or one
exclusive migration action: --rollback-codex-skills / --rollback-config-schema-v1.
Host task-tool guard (whole command): the numbered steps below are the complete execution plan.
Do not call any host task/todo-tracking tool, including but not limited to TaskCreate,
TaskUpdate, TaskList, TaskGet, and TodoWrite, and do not discover such a tool just to mirror
this plan. These tools are not required for updating and may be absent from the live
discovered-tool set. A live-schema user-question tool is allowed only at a step below that
explicitly requires the user's choice (for example the per-file conflict choice in Step 2 or the
C5 migration adjudication in Step 2.C); do not invent any other interactive decision.
Step 0 — Orphaned-root guard
If ${CLAUDE_PLUGIN_ROOT}/.orphaned_at exists, abort immediately: the resolved plugin root is
an orphaned cache snapshot (the plugin was updated mid-session and the harness still points at the
old dir). Comparing against it silently reports everything up-to-date against a stale version.
Tell the user: "plugin root is an orphaned snapshot — restart the session / reload plugins, then
re-run /sop-update." Do not auto-resolve to a sibling live directory.
Before any Codex skill lifecycle decision, read
${CLAUDE_PLUGIN_ROOT}/templates/control-surface/codex-skill-host-contract.md. Its minimum CLI,
canonical/legacy roots, five-entry set, preserve-only gate behavior, and rollback flag are the
machine-derived authority; do not reconstruct those facts from this prose.
Step 1 — Read the manifest
Read .ccsop/manifest.json. If absent, tell the user to run /sop-init first and stop.
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.
- 3d ago First seen · 495 lines · 89 tokens per session scan A a80b549bf5a2
sop-update is a command published in the GitHub repository Gnayj/claude-code-sop (2 stars, last pushed 22d ago), licensed MIT. It adds 89 tokens to every session and 9,084 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.