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/saski/arnesto/creating-process-filesnpx skills add saski/arnesto --skill creating-process-filesgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/creating-process-files)<a href="https://agentmods.dev/skills/saski/arnesto/creating-process-files"><img src="https://agentmods.dev/badge/skills/saski/arnesto/creating-process-files.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 | $0.00024 | $0.00513 |
| Opus 5 | $0.00012 | $0.00257 |
| Sonnet 5 | $0.00005 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
creating-process-files 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.
This is a copy
100% identical to creating-process-files — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Process Files
STARTER_CHARACTER = ⚙️
Description
This skill helps make new process files or fine tune existing ones. A process file describes a structured sequence of steps for AI to follow to create a predictable output. Process files are content neutral to the project.
Steps
This process has these distinct phases:
- Interview Phase - Ask for the pieces of the process file that we are going to build
- Draft Phase - Create the initial version of the process file
- Clarification Phase - Ask any clarifying questions about the process file
- Simplification Phase - Remove unnecessary content
Pieces
- [FILE_NAME]
- [HEADER]
- [STARTER_CHARACTER]
- Steps
- Title
- Details
- Sub-steps (optional)
- [DESCRIPTION]
Interview Protocol
Ask one question at a time. If you are giving options, give a list to choose from.
Phases
Phase 1: Interview
- Read the provided file, and ask for the [FILE_NAME] if not provided.
- Ask for the [HEADER] for the file.
- Ask for a small [DESCRIPTION] of what this process is going to achieve.
- Ask for the [STARTER_CHARACTER] emoji. A STARTER_CHARACTER is a marker (usually an emoji) that appears at the beginning of each response to indicate that the context window is intact and rules are being followed. Suggest 5-8 appropriate emoji based on the process topic.
- We need a list of steps. Ask for each step in the process, one at a time. If anything is unclear about a step, ask clarifying questions.
- Identify any missing steps that would achieve the stated description of the process.
Phase 2: Draft
Create the initial version of the process file, or revise it if it already exists. Ask to review it.
Phase 3: Clarification
Read the draft created in phase 2. Check for inconsistencies, contradictions, or missing information. If any are found, ask clarifying questions one at a time.
Phase 4: Simplification
Review the process file created in phase 2 and simplify. Be as concise as possible.
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.
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 · 70 lines · 24 tokens per session scan A 220012270db8
creating-process-files is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 8d ago), licensed Unlicense. It adds 24 tokens to every session and 513 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to creating-process-files, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
pixir-delegate
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…
pixir-delegate-codex
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…
pixir-diagnostics
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
pixir-delegate-native
Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.