agentic-stack is a portable layer of agent memory, skills, and protocols stored in a .agent/ folder that can be used across multiple coding-agent tools. It is for people who switch between agent harnesses while keeping shared knowledge and monitoring data. The catalogue entries provide skills and rules for this shared agent layer.
Borrowing it
Nothing to install: this file belongs to codejunkie99/agentic-stack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/codejunkie99/agentic-stack/master/.agent/skills/data-flywheel/SKILL.mdgit clone --depth 1 https://github.com/codejunkie99/agentic-stackWrote 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/codejunkie99/agentic-stack/data-flywheel)<a href="https://agentmods.dev/skills/codejunkie99/agentic-stack/data-flywheel"><img src="https://agentmods.dev/badge/skills/codejunkie99/agentic-stack/data-flywheel/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/codejunkie99/agentic-stack/data-flywheel"><img src="https://agentmods.dev/badge/skills/codejunkie99/agentic-stack/data-flywheel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Rogue Agent · line 108 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00004 | $0.00740 |
| Opus 5.5 | $0.00002 | $0.00296 |
| Sonnet 5.5 | $0.00001 | $0.00148 |
| Haiku 4.5 | $0.00000 | $0.00074 |
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 1mo 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 — 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:
domainworkflowharnessinstructioninput_redactedoutput_approvedhuman_review.statusasacceptedoreditedredaction_status: passedpii_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.jsonltraining-examples.jsonleval-cases.jsonlcontext-cards/<domain>/<workflow>.mdcontext-cards/<domain>/<workflow>.jsonflywheel-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
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.
- 1mo ago First seen · 113 lines · 4 tokens per session scan A add01625fbaa
data-flywheel is a skill published in the GitHub repository codejunkie99/agentic-stack (2,302 stars, last pushed 9d ago), licensed Apache-2.0. It adds 4 tokens to every session and 740 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other skills, from other repositories
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
llm-security
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
llm-ops
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.