Frontier Workflow Mode

Frontier Workflow Mode is a skill for Claude Code from ralfyishere/rules-with-receipts. It costs 120 tokens per session (1,946 once invoked), scanned A, original, MIT.

A high-rigor workflow for complex, risky, ambiguous, or quality-sensitive technical work. It runs the relevant skills in a defined order so important checks are not skipped.

In plain words
What is it for?
Use it for production changes, architecture decisions, strategy documents, major features, migrations, hard bugs, and other multi-step work where careful review is warranted.
Why use it?
Major features, migrations, difficult bugs, and work that others will act on need more than a quick answer. This workflow adds structure when mistakes would be costly or hard to undo.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

Good fit Use it for production changes, architecture decisions, strategy documents, major features, migrations, hard bugs, and other multi-step work where careful review is warranted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ralfyishere/rules-with-receipts/frontier-workflow-mode
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 ralfyishere/rules-with-receipts --skill frontier-workflow-mode
Clone the repo
git clone --depth 1 https://github.com/ralfyishere/rules-with-receipts

Made for: Claude Code.

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.

agentmods badge for Frontier Workflow Mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/frontier-workflow-mode/github.svg)](https://agentmods.dev/skills/ralfyishere/rules-with-receipts/frontier-workflow-mode)
Your own site
<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/frontier-workflow-mode"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/frontier-workflow-mode/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.

agentmods 80×15 button for Frontier Workflow Mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/frontier-workflow-mode"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/frontier-workflow-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,946 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.01946
Opus 5 $0.00060 $0.00973
Sonnet 5 $0.00024 $0.00389
Haiku 4.5 $0.00012 $0.00195

Measured 9d ago against content hash 2b5efd418b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Frontier Workflow Mode 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 9d 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.

.claude/skills/frontier-workflow-mode/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontier Workflow Mode

Purpose

One operating procedure that sequences the whole pack so that important work gets every discipline, in the right order, without re-deciding the process each time. This is not a special ability — it is the ordinary skills, run in sequence, with none skipped. Its value is exactly that: on high-stakes work, the steps you're tempted to skip are the ones that were going to catch the problem.

When to use this skill

  • Any task effort-calibration rates High or Critical.
  • Explicit user signals: "important", "be thorough", "production", "for the board", "get this right".
  • Structural signals: multi-step and ambiguous; consequences hard to reverse; output will be acted on by others; quality-sensitive deliverables (strategy, architecture, public writing).

When NOT to use this skill

  • Low/Medium-tier tasks. Running the full pipeline on a quick question is the over-effort failure effort-calibration exists to prevent. Most tasks should NOT be in this mode.
  • When the user explicitly wants speed or a rough draft — honor that; offer the rigorous pass as a follow-up.

Operating procedure

Run the phases in order. Each phase is one sibling skill doing its job at normal depth — the mode adds sequencing, not ceremony. Skippable phases are marked; skipping is a decision to state, not a drift.

Phase Skill What it contributes here Skippable?
1 intent-clarity The mission, constraints, and stated interpretation. Everything downstream inherits this — an error here poisons all of it Never
2 effort-calibration Confirms the tier (this mode = High/Critical) and sets verification depth Never
3 plan-gate Written plan: success criteria, assumptions, risks. Include a failure-mode-awareness pass on the plan's risk section Never in this mode
4 deep-decomposition Stages with outputs and dependency order — only if the task exceeds one plan If task fits one plan
5 live-state-truth Ground the plan: verify cheap assumptions, read actual current state before executing. Then execute — with scope-fence and change-control as standing constraints on every edit Never
6 verification-discipline Label the claims in the emerging result: fact / inference / assumption / guess; upgrade what's cheap to upgrade Never
7 adversarial-verify Attack the finished work: edge cases, counterexamples, alternative explanations; test attacks by execution Never in this mode
8 ruthless-editor Cut and strengthen the deliverable's prose without losing calibration If output is code-only
9 output-structuring Shape for the reader's next action; lead with the outcome Never
10 self-improvement-loop Close out: if anything failed or got corrected en route, extract the lesson If nothing failed

Read the full file on GitHub · 85 lines

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.

  1. 9d ago First seen · 85 lines · 0 tokens per session scan A 2b5efd418b27

Subscribe to this mod's changes

Frontier Workflow Mode is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,946 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.

Related

Other skills, from other repositories

happiness-skill

A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.

kangarooking/cangjie-skill · 136 tokens

setup-matt-pocock-skills

A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.

devcxl/mattpocock-skills-zh · 43 tokens

frontend-design

A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.

AnastasiyaW/codex-claude-code-config · 264 tokens

alterlab-cobrapy

Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…

AlterLab-IEU/AlterLab-Academic-Skills · 91 tokens

alterlab-depmap

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…

AlterLab-IEU/AlterLab-Academic-Skills · 77 tokens

alterlab-qutip

Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…

AlterLab-IEU/AlterLab-Academic-Skills · 134 tokens