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 valtterimelkko/agent-workflow-skills --skill claude-pgit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skillsWrote 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/valtterimelkko/agent-workflow-skills/claude-p)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/claude-p"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/claude-p/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/valtterimelkko/agent-workflow-skills/claude-p"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/claude-p.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 | $0.00121 | $0.02393 |
| Opus 5 | $0.00060 | $0.01196 |
| Sonnet 5 | $0.00024 | $0.00479 |
| Haiku 4.5 | $0.00012 | $0.00239 |
Grade A, and why
claude-p 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 10d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude -p Skill
A reference for using claude -p (non-interactive print mode) to run Claude Code sessions programmatically — particularly for multi-turn conversations in server-side code.
This is the direct CLI approach, not the Claude Agent SDK. The key binary is claude, authenticated via claude auth login (subscription auth).
Core invocation
claude -p "your prompt" \
--output-format stream-json \
--verbose \
--permission-mode acceptEdits \
--model sonnet \
--session-id <uuid> # first turn only — see below
--output-format stream-json --verbose is required together: stream-json alone is rejected in -p mode without --verbose.
Auth: subscription, not API key
const env = { ...process.env };
delete env.ANTHROPIC_API_KEY; // forces subscription auth
delete env.ANTHROPIC_AUTH_TOKEN; // forces subscription auth
// Claude reads <CLAUDE_HOME>/ credentials automatically
Check auth status:
claude auth status --json # correct flag
# NOT: --output-format json # wrong, will error
Multi-turn sessions — the critical distinction
Claude Code uses a per-session-id file lock. The lock persists for several seconds (sometimes indefinitely) after the subprocess exits. This is the single most common source of failures.
Rule: first turn vs follow-up turns
| Turn | Flag | Why |
|---|---|---|
| First | --session-id <uuid> |
Creates the session file |
| Follow-up | --resume <uuid> |
Continues without triggering the lock |
--session-id on a follow-up always fails with "Session ID already in use" — even seconds after the first process exited.
const sessionFlag = isFirstTurn
? ['--session-id', claudeSessionId]
: ['--resume', claudeSessionId];
spawn('claude', ['-p', prompt, '--output-format', 'stream-json',
'--verbose', '--permission-mode', 'acceptEdits',
'--model', model, ...sessionFlag], { ... });
Track "has had a first turn" per session:
private sessionsWithHistory = new Set<string>();
// After successful first turn:
sessionsWithHistory.add(sessionId);
// On subsequent turns: isFirstTurn = !sessionsWithHistory.has(sessionId)
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.
- 10d ago First seen · 258 lines · 121 tokens per session scan A c055adefe44a
claude-p is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 2,393 once invoked, about $0.0006 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…
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…
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…