Borrowing it
Nothing to install: this file belongs to DariuszNewecki/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/DariuszNewecki/CORE/main/CLAUDE.mdgit clone --depth 1 https://github.com/DariuszNewecki/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/dariusznewecki/core/claude-md)<a href="https://agentmods.dev/instructions/dariusznewecki/core/claude-md"><img src="https://agentmods.dev/badge/instructions/dariusznewecki/core/claude-md/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/instructions/dariusznewecki/core/claude-md"><img src="https://agentmods.dev/badge/instructions/dariusznewecki/core/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01943 | $0.01943 |
| Opus 5.5 | $0.00777 | $0.00777 |
| Sonnet 5.5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
CORE CLAUDE.md 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 5d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — CORE
v3 done; CORE 3.1 in progress (since 2026-10-29)
The freeze ended 2026-10-29: every v3 gate issue is closed (milestone
CORE 3.0: 48 closed, 0 open). Work is filed in milestone CORE 3.1. No new features
before the v3 release. New infrastructure (timers, crons, credentials,
services) needs the governor's yes first. The PR check freeze-scope still
refuses a PR whose description names no v3 or CORE 3.1 issue.
CORE is a Python runtime that audits a codebase against rules in .intent/, records
violations in PostgreSQL, proposes fixes, and logs the chain from finding to commit.
Layout
src/api/ FastAPI routes; DB access only via api/dependencies.py
src/body/ atomic actions, services, workers (execution)
src/mind/ rule engines; read .intent/, no I/O or execution
src/will/ agents and autonomous orchestration
src/shared/ common substrate; must not import mind/body/will
src/cli/ Typer commands; Rich rendering only here
.intent/ rules and config the runtime reads (YAML/JSON)
.specs/ design history (ADRs, papers); reference, not instructions
Facts (update when they change)
- PyPI:
core-runtime3.1.0 (2026-11-03; consumer: proof run 10). - Latest proof run: 9 (#1053, 2026-10-30, on 3.0.0 from PyPI); gate met, no issues filed. Next run: 10.
- Production-ready (docs/release.md): stays Beta until an independent person, not an AI agent, installs CORE from the README and uses it.
- Credentials: a closed list (governor 2026-10-23). No new token, no permission
change, never asked of the governor. A job uses one of these and checks it at
start, failing loudly if it does not work.
- core-claude-bot gh login (core-claude; scopes repo, workflow, read:org):
pushes branches, opens PRs into main and turns on their auto-merge,
creates
promote/<sha>branches, opens or updates the promotion PR, and closes a superseded one and deletes its branch. After review finding F2: also opens the PR for CORE's generated tests. The 06:00 job hands this login's token topromote proposeasCORE_GITHUB_TOKEN. Every 15 minutesinfra/scripts/core_alert_check.pyopens and closes the[alert]issues that mention the governor (review F4); no new credential. - CORE's own token (CORE daemon): read as
CORE_GITHUB_TOKENfrom the environment, else the unit credentialgithub-token(delivery_branch.py). Pushes CORE's branches; cannot open PRs (#1252). Same variable name as above, a different credential. /etc/core/pipeline-github-token(core-runner): an issues-only token on the governor's own account (#1198); it opens the issue for a failed promotion, and every other pipeline read is unauthenticated. GitHub sends no email for one's own issue, so an alert meant to reach the governor is opened as core-claude-bot (#1201 was opened as the governor)./etc/core/pipeline-deploy-key(core-runner): the write deploy key; moveslive. Rulesetlive-writerslets any write deploy key do so; this is the only one (governor counted, 2026-10-23), and it stays the only one.- Deliberately not on the list: the governor's own GitHub login, the
built-in
GITHUB_TOKENof Actions jobs, and PyPI (Trusted Publishing, no stored token).
- core-claude-bot gh login (core-claude; scopes repo, workflow, read:org):
pushes branches, opens PRs into main and turns on their auto-merge,
creates
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.
- 5d ago Changed · +7 tokens per session 2709830de344
- 7d ago Changed · +4 lines · +96 tokens per session a59014019cfe
- 8d ago Changed · +2 lines · +27 tokens per session ec6d25b0cfab
- 9d ago Changed b3669a60346c
- 10d ago Changed · -1 lines · -37 tokens per session a5f815e58e85
- 16d ago Changed · +41 lines · +755 tokens per session 8fbe4b688ca2
- 20d ago Changed · +6 tokens per session 91909371cb4b
- 21d ago Changed · +24 lines · +343 tokens per session 373f712ecdf0
- 26d ago Changed · -478 lines · -8,121 tokens per session scan B → A f4ae8362ec83
- 27d ago First seen · 544 lines · 8,867 tokens per session scan B fd058a96f9d6
CORE CLAUDE.md is an instructions file published in the GitHub repository DariuszNewecki/CORE (39 stars, last pushed yesterday), licensed MIT. It adds 1,943 tokens to every session, about $0.0078 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.
CORE CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| CORE CLAUDE.mdDariuszNewecki/CORE | Instructions file | 39 | yesterday | MIT | A | 1,943 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |