fastworkflow: Skill for Claude Code

.claude/skills/fastworkflow-research-methodology/SKILL.md

fastworkflow-research-methodology is a skill for Claude Code from radiantlogicinc/fastworkflow. It costs 175 tokens per session (6,183 once invoked), scanned A, original, Apache-2.0.

A research method for testing ideas in the fastWorkflow codebase, including forming hypotheses, running experiments, and deciding whether results should be accepted or retired. It requires recording measured results and uncertainty.

In plain words
What is it for?
Use it to plan experiments, define success criteria, document numbers and intervals, review evidence, and decide whether a research result is reliable enough to keep.
Why use it?
It helps distinguish a genuine improvement from a lucky or misleading score. This makes experiments reproducible and their conclusions easier to review.

Skill for Claude Code

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

This is radiantlogicinc/fastworkflow's own configuration. It tells Claude Code how to work on fastworkflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fastworkflow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to radiantlogicinc/fastworkflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/radiantlogicinc/fastworkflow/main/.claude/skills/fastworkflow-research-methodology/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/radiantlogicinc/fastworkflow

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 fastworkflow-research-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-research-methodology.svg)](https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-research-methodology)
Your own site
<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-research-methodology"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-research-methodology.svg" alt="Measured on agentmods" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,183 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
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 $0.00175 $0.06183
Opus 5 $0.00088 $0.03092
Sonnet 5 $0.00035 $0.01237
Haiku 4.5 $0.00017 $0.00618

Measured 8d ago against content hash a4f3c26de557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fastworkflow-research-methodology 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/lint_experiment_doc.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/fastworkflow-research-methodology/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TEAM-PRIVATE: embeds content from uncommitted internal docs. Do not commit or publish this skill without the developer'sexplicit approval.

fastWorkflow Research Methodology

The discipline that turns a hunch into an accepted result in this repo — or into a documented retirement. This is the constitution; the tau2-reliability-campaign skill is the worked application of it.

The house summary, from the plan's own documentation standard: "if it isn't written here with a number and an interval, it didn't happen" (docs/tau2_retail_reliability_implementation_plan.md, Appendix G).

When to use / when NOT to use

Situation Skill
You have an idea and want to know how to make it an accepted result here this skill
You are running the E0–E25 retail reliability experiments in order tau2-reliability-campaign
You need the actual variance / pass^k / McNemar / CI math with worked examples fastworkflow-proof-and-analysis-toolkit
You want to know which open problems are worth attacking fastworkflow-research-frontier
You need tau-bench mechanics (harness, simulator, pass@1 vs pass^k, parity rules) fastworkflow-taubench-reference
You need what counts as test evidence / how to add pytest tests fastworkflow-validation-and-qa
Your change is code, not research — how it gets classified/gated/reviewed fastworkflow-change-control
You want the history of every dead end and abandoned feature fastworkflow-failure-archaeology
You are writing a design doc or deciding what may be claimed publicly fastworkflow-docs-and-positioning

Glossary (define once, use everywhere)

Term Meaning
pass@1 / pass^k pass@1 = fraction of tasks passing one run. pass^k = fraction passing all k independent runs. pass^k measures reliability; pass@1 measures capability.
τ²-bench retail Public benchmark: agent plays a retail customer-service rep against a simulated user (another LLM). Scoring is binary and conjunctive on final DB state — one wrong write = 0 for the task.
The 15 hard tasks Hand-picked τ²-retail task IDs that failed under memory pressure (plan Appendix F). An adversarial sample AND our months-long tuning set — which is why anti-p-hacking rules exist.
bd (beads) The issue tracker (bd CLI, source of truth .beads/issues.jsonl). Mandatory for ALL tracking (AGENTS.md).
E-card Experiment card: the plan's unit of proposed work (E0–E25 in docs/tau2_retail_reliability_implementation_plan.md §7). Hypothesis with predicted numbers, design, metrics, gate criteria, dependencies.
Pre-registration Writing hypothesis + config + metrics + analysis plan, and committing it, before the run.
Adversarial review A reviewer (human or agent) explicitly tasked to refute a design against the actual working tree at a pinned commit — the fix-vof pattern.
McNemar / Clopper-Pearson / Wilson Paired before/after significance test; exact/approximate confidence intervals on proportions. Recipes in fastworkflow-proof-and-analysis-toolkit.
Ablation Measuring one change at a time so effects are attributable.
RSI Recursive self-improvement — here always bounded and for reliability (E21), never free-running.

Read the full file on GitHub · 242 lines

Files

What ships with it

3 files 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.

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. 8d ago First seen · 242 lines · 175 tokens per session scan A a4f3c26de557

Subscribe to this mod's changes

fastworkflow-research-methodology is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 175 tokens to every session and 6,183 once invoked, about $0.0009 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens