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/gnayj/claude-code-sop/project-sopnpx skills add Gnayj/claude-code-sop --skill project-sopgit 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/skills/gnayj/claude-code-sop/project-sop)<a href="https://agentmods.dev/skills/gnayj/claude-code-sop/project-sop"><img src="https://agentmods.dev/badge/skills/gnayj/claude-code-sop/project-sop.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 5.1 | $0.00052 | $0.00946 |
| Opus 5 | $0.00026 | $0.00473 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
project-sop 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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project SOP Skill
The repository's in-repo workflow skill — an execution map that points at the rule source of
truth; it does not embed rule text (single source = docs/methodology/, to avoid drift).
Design principles:
docs/methodology/project-delivery-sop.mdis the single source of SOP rules; this skill is a map + section pointers only.- Prioritize not regressing execution.
docs/records/current.mdis the live state breakpoint.
Collaboration mode
The default is driver-led (the driver does design / cards / implement / fix / closeout; the
reviewer does code review + design pre-review). Review is delivered manually
(review.provider=manual) or automatically via the review MCP bridge (review.provider ∈ {codex, claude}). A reviewer-led fallback also exists. Full definitions + switching:
docs/methodology/claude-code-sop-collaboration.md §1.
Execution entry
- Startup order:
- prefer invoking
/handofffor current state + active-task summary + locked decisions + next step (saves ~70% startup tokens); - or read
docs/records/current.mddirectly when full context is needed; - then the topic doc for this module;
- read
docs/records/archive/<period>.mdonly to trace history; - before implement / fix, read the full task card (handoff is not ground truth).
- when comparing Claude commands with Codex skills or diagnosing Codex discovery, read
${CLAUDE_PLUGIN_ROOT}/templates/control-surface/codex-skill-host-contract.md; do not infer host-only/parity policy, invocation aliases, roots, or required entries from memory.
- prefer invoking
- Task-card decision (design vs implement):
- single-round (N=1): no implement card; fold the closeout summary into the design's implementation-record.
- multi-round / relay (N≥2): one implement card per phase (from
docs/plans/_template-implement.txt). - criteria:
claude-code-sop-collaboration.md §4.1.
current.mddiscipline: keep only current state / recently accepted / current testing / real next step / key interfaces / key docs / resume template; move accepted-but-stale items to archive; no completed phases, long logs, or mis-set statuses incurrent.md.- Default action: when asked to "proceed per the SOP", follow the active collaboration mode's role split; do not take over an action assigned to the other role — report and let the user switch modes or hand off.
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.
- 5d ago First seen · 75 lines · 52 tokens per session scan A bbc50582462a
project-sop is a skill published in the GitHub repository Gnayj/claude-code-sop (2 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 946 once invoked, about $0.0003 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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…
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…