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.
curl -O https://raw.githubusercontent.com/tatargabor/set-core/main/CLAUDE.mdgit clone --depth 1 https://github.com/tatargabor/set-coreWrote 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/instructions/tatargabor/set-core/claude-md)<a href="https://agentmods.dev/instructions/tatargabor/set-core/claude-md"><img src="https://agentmods.dev/badge/instructions/tatargabor/set-core/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.08495 | $0.08495 |
| Opus 5 | $0.04248 | $0.04248 |
| Sonnet 5 | $0.01699 | $0.01699 |
| Haiku 4.5 | $0.00850 | $0.00850 |
Grade B, and why
set-core CLAUDE.md scanned grade B 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` already carries `"language": "English"`, so the harness agrees with the How it starts
The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠ ACTIVE TRACK — highest priority while it is open
The consumer ↔ set-core integration. Its living record is
docs/integration/consumer-integration.md.
Read it before deciding what to do next, and update it as part of the work, not after —
a step that is done but unrecorded is indistinguishable from one that was never taken.
It holds what is shipped and verified, what is agreed with the consumer, the decisions
taken and why, and the ordered next steps. The goals and constraints below outrank it.
The user has delegated the decisions on this track (2026-07-24): decide from the experience already on the record rather than escalating. That is a mandate to choose, not to guess — a decision made this way names the evidence it rests on and goes in the living record, so it can be revisited rather than merely inherited.
Write it down BEFORE the context ends, and read it back after (user, 2026-07-24). The danger on this track is not forgetting — it is compounding: every hop through a compact, through the agent channel, or through a scratch file that evaporates loses precision while keeping confidence, so a diluted claim gets built on as if it were the measurement. Three consequences, all binding:
- Record at the moment of the decision or the measurement, not at the end of the step.
- On resuming, re-check rather than re-derive — every claim in the living record names how it was verified, and re-running that check costs seconds.
- A summary is not a source. When your recollection and the living record disagree, the record wins unless you can produce evidence — and then you fix the record immediately.
What counts as knowing something — the defect classes that keep recurring here, and how to
prove a fix is a fix — is in
.claude/rules/evidence-discipline.md.
The goal this work serves — do not lose this across a compact (2026-07-24)
The user has stated this twice, emphatically, because a context boundary is exactly where an agreed goal quietly turns into whatever the current task happens to be. The goals below survive the compact; the task in flight does not outrank them.
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.
- today First seen · 524 lines · 8,495 tokens per session scan B c676025869fb
set-core CLAUDE.md is an instructions file published in the GitHub repository tatargabor/set-core (35 stars, last pushed today), licensed MIT. It adds 8,495 tokens to every session, about $0.0425 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.