data-layer

A local monitoring and reporting layer for coding agents, including Claude Code, Hermes, OpenClaw, Codex, Cursor, OpenCode, Windsurf, Pi, Antigravity, and custom loops. It reads agent activity from local `.agent` data and summarises runs, usage, costs, and reliability.

In plain words
What is it for?
Use it to track active agents, scheduled runs, event volume, token use, estimated costs, resource categories, workflow errors, and success rates. It can also produce terminal dashboards and screenshot-ready daily reports.
Why use it?
It gives a view across different agent tools instead of making you inspect each one separately. It also keeps monitoring local and avoids sending telemetry or storing raw prompts and code in shared examples.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 2 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 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 $0.00002 $0.01099
Opus 5 $0.00001 $0.00549
Sonnet 5 $0.00000 $0.00220
Haiku 4.5 $0.00000 $0.00110

Measured 2d ago against content hash 7d5f77659ba6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-layer 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 2d 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.

.agent/skills/data-layer/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Layer - cross-harness monitoring for the portable brain

Use this skill when the user wants to measure agent activity across Claude Code, Hermes, OpenClaw, Codex, Cursor, OpenCode, Windsurf, Pi, Antigravity, or any custom loop using .agent/.

The goal is local business intelligence for the whole agent suite:

  • what harnesses are active
  • how many agent events are happening
  • when cron/scheduled agents fire
  • which crons started/finished and how long they ran
  • how many agents are active
  • tokens and estimated cost by hour/day/week/month
  • resource usage by user-defined category
  • workflow success/error rates
  • KPI summary rows for cron cadence, run volume, reliability, active agents, workflow breadth, token usage, and estimated cost
  • terminal dashboard visible directly in the user's coding tool
  • screenshot-ready daily resource reports

Hard Rules

  • Stay local-first. Do not add telemetry or remote sync.
  • Do not store raw prompts, raw code, client names, emails, phone numbers, or unredacted business records in shared examples.
  • Do not commit .agent/data-layer/ exports unless the user explicitly reviewed and sanitized them.
  • Do not send dashboard screenshots to email, Slack, webhooks, or any other channel unless the user explicitly approves the destination.

Inputs

Default inputs:

.agent/memory/episodic/AGENT_LEARNINGS.jsonl
.agent/data-layer/harness-events.jsonl     optional
.agent/data-layer/cron-runs.jsonl          optional
.agent/data-layer/category-rules.json      optional

AGENT_LEARNINGS.jsonl is the shared activity log. Optional files let users add events from harnesses that do not automatically write rich events yet.

Agent behavior

When this skill is injected, decide whether the user is asking to see local agent activity. Natural prompts such as "what did my agents do", "show me the dashboard", "how many tokens did we use", or "show last week by hour" should render the terminal dashboard directly. Do not make users remember flags.

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 2 tokens per session scan A 7d5f77659ba6

Subscribe to this mod's changes

data-layer is a skill published in the GitHub repository codejunkie99/agentic-stack (2,241 stars, last pushed 26d ago), licensed Apache-2.0. It adds 2 tokens to every session and 1,099 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.

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