set-core: Skill for Claude Code

.claude/skills/e2e-runs/SKILL.md

e2e-runs is a skill for Claude Code from tatargabor/set-core. It costs 74 tokens per session (1,360 once invoked), scanned A, original, MIT.

A guide for starting, comparing, and diagnosing end-to-end runs, which test a complete application flow rather than one small function. It also covers running Playwright tests for a web dashboard; Playwright is a tool for controlling a browser in tests.

In plain words
What is it for?
Use it to supervise orchestration runs, scan their results, compare two runs, or test dashboard changes with Playwright.
Why use it?
It gives developers a repeatable way to inspect run logs, find framework bugs, compare runs, and collect fixes from consumer projects.

Skill for Claude Code

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

This is tatargabor/set-core's own configuration. It tells Claude Code how to work on set-core 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 set-core configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./tests/e2e/runners/run-micro-web.sh # scaffold + init + register.

Reuse

Borrowing it

Nothing to install: this file belongs to tatargabor/set-core. 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/tatargabor/set-core/main/.claude/skills/e2e-runs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tatargabor/set-core

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 e2e-runs

README.md
[![agentmods](https://agentmods.dev/badge/skills/tatargabor/set-core/e2e-runs.svg)](https://agentmods.dev/skills/tatargabor/set-core/e2e-runs)
Your own site
<a href="https://agentmods.dev/skills/tatargabor/set-core/e2e-runs"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/e2e-runs.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 4 findings, 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 Data Exfiltration · line 73
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Rogue Agent · line 77
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium MCP Rug Pull · line 106
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 109
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00074 $0.01360
Opus 5 $0.00037 $0.00680
Sonnet 5 $0.00015 $0.00272
Haiku 4.5 $0.00007 $0.00136

Measured yesterday against content hash 8b684a93cd71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

e2e-runs scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://localhost:7400/api/<project>/sentinel/start \
.claude/skills/e2e-runs/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E runs, run diagnostics, and the dashboard's Playwright suite

Moved out of CLAUDE.md on 2026-08-22 so it loads when it is needed rather than in every session. Nothing was cut — the text below is those three sections verbatim.

Consumer Project Diagnostics

set-core is developed and battle-tested through consumer projects. Before fixing bugs or adding features, always consult the primary consumer for real-world diagnostics.

Harvest (primary tool)

After every E2E run, use set-harvest to scan consumer projects for framework-relevant fixes:

set-harvest                          # scan all registered consumer projects
set-harvest --project craftbrew-run-20260320-1445 # scan single project
set-harvest --dry-run                # preview without updating state

The harvest tool scans ISS fix commits, classifies them (framework-relevant vs project-specific), and presents them for interactive adoption into planning rules, templates, or core code.

Manual workflow

  1. Read the latest orchestration run log — each log has a "set-core Bugs to Report" section and "Conclusions for set-core Development" with prioritized issues, root cause analysis, and design decisions.
  2. Diff .claude/ for upstream changes — during orchestration, the sentinel or user may improve commands, skills, or configs in the consumer's .claude/. Diff against set-core source to find changes to adopt.
  3. Check orchestration.yaml — the consumer's config reflects production usage. Understand what directives are actually used before changing defaults.
  4. Use run comparison data — run logs contain quantitative comparisons (wasted iterations, token efficiency, intervention count). Use these to validate whether a fix actually improved things.

Bidirectional flow

set-core (source)                     consumer project
   │                                      │
   ├── set-project init ──────────────────►│  deploy .claude/ files
   │                                      │
   │◄── run logs (bugs, design) ──────────┤  diagnostics after each run
   │◄── .claude/ diffs ──────────────────┤  sentinel/user improvements
   │◄── orchestration.yaml ──────────────┤  config evolution
   │                                      │
   ├── fix bugs, add features             │
   ├── set-project init ──────────────────►│  redeploy

Read the full file on GitHub · 119 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 · 119 lines · 74 tokens per session scan A 8b684a93cd71

Subscribe to this mod's changes

e2e-runs is a skill published in the GitHub repository tatargabor/set-core (35 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,360 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.