agentmods.dev

data-flywheel

A workflow for turning approved work by coding agents into private, reusable records for search, evaluation, prompt improvement, and possible later model experiments.

In plain words
What is it for?
Use it to redact approved runs, create context cards and evaluation cases, and generate training-ready JSONL files without training a model.
Why use it?
It prevents useful past work from being lost while requiring sensitive data and unapproved runs to stay out of training material.

Skill for Claude CodeCodex

2.2k 25d ago A scan 4 tokens original Apache-2.0
View the source file codejunkie99/agentic-stack
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.

agentmods
npx agentmods add skills/codejunkie99/agentic-stack/data-flywheel
Any agent
npx skills add codejunkie99/agentic-stack --skill data-flywheel
Clone the repo
git clone --depth 1 https://github.com/codejunkie99/agentic-stack

Made for: Claude Code, Codex.

Per session 4 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 740 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00004 $0.00740
Opus 5 $0.00002 $0.00370
Sonnet 5 $0.00001 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured yesterday against content hash add01625fbaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-flywheel 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 yesterday.

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.

.agent/skills/data-flywheel/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Flywheel - approved runs into reusable intelligence

Use this skill when a user wants to turn repeated human-approved agent work across Claude Code, Hermes, OpenClaw, Codex, Cursor, or custom .agent/ loops into local artifacts for retrieval, evals, prompt shrinking, and optional future open-weight model/adapters.

The flywheel is:

approved run
-> redacted trace
-> context card
-> eval case
-> training-ready JSONL
-> optional downstream SLM/adapter experiment later

This skill creates the harness. It does not train a model.

Hard Rules

  • Use only human-approved runs. Rejected or unknown-review runs can become failure-mode notes, not trainable examples.
  • Redaction must pass before anything is marked trainable.
  • Do not store raw prompts, raw code, client names, addresses, phone numbers, emails, secrets, credentials, or unredacted CRM records.
  • Keep .agent/flywheel/ private and gitignored unless the user explicitly commits sanitized examples.
  • Stay model-agnostic. Mention model families only as downstream examples.

Inputs

Default local input:

.agent/flywheel/approved-runs.jsonl

Each line should be a sanitized run record with:

  • domain
  • workflow
  • harness
  • instruction
  • input_redacted
  • output_approved
  • human_review.status as accepted or edited
  • redaction_status: passed
  • pii_level
  • optional stable_rules, tool_contracts, eval_tags, failure_modes

Export

Run:

python3 .agent/tools/data_flywheel_export.py

Outputs go to:

.agent/flywheel/exports/<YYYY-MM-DD>/

Key outputs:

  • trace-records.jsonl
  • training-examples.jsonl
  • eval-cases.jsonl
  • context-cards/<domain>/<workflow>.md
  • context-cards/<domain>/<workflow>.json
  • flywheel-metrics.json

Readiness Checks

Use these as heuristics, not hard rules:

  • 10-25 approved runs: useful first context card
  • 25-100 approved runs: first eval set and repeated failure modes
  • 100-300 approved runs: context compression and routing measurement
  • 500-1,500 high-quality examples: narrow adapter experiment candidate
  • 2,000-10,000+ examples: broader workflow-family corpus

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 4 tokens per session scan A add01625fbaa

Subscribe to this mod's changes

data-flywheel is a skill published in the GitHub repository codejunkie99/agentic-stack (2,241 stars, last pushed 25d ago), licensed Apache-2.0. It adds 4 tokens to every session and 740 once invoked, about $0.0000 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.

Data and AIProductivityResearch
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

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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens