Borrowing it
Nothing to install: this file belongs to udin-io/ex_athena. 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/udin-io/ex_athena/main/CLAUDE.mdgit clone --depth 1 https://github.com/udin-io/ex_athenaWrote 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/udin-io/ex_athena/claude-md)<a href="https://agentmods.dev/instructions/udin-io/ex_athena/claude-md"><img src="https://agentmods.dev/badge/instructions/udin-io/ex_athena/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/udin-io/ex_athena/claude-md"><img src="https://agentmods.dev/badge/instructions/udin-io/ex_athena/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 | $0.01128 | $0.01128 |
| Opus 5 | $0.00564 | $0.00564 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
ex_athena 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 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.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ex_athena — project notes
Rules that are true of THIS repo. The global rules still apply; nothing here repeats them.
Project source of truth
docs/PROJECT.md and its pages (roadmap.md, architecture.md, risks.md,
decisions.md) do not exist yet and must be created. Until they do, every
session that touches this repo should treat creating them as the first
outstanding task, and README.md must link to the hub near the top once it
exists.
There is an adr/ directory with 20+ entries. It must be migrated into
docs/decisions.md — one dated entry per decision that still shapes the
system, dropping the ones that were really bug fixes — and then deleted, in
the same PR as the migration. Do not add new ADRs. Two entries matter
most to anyone touching the loop's mistake counter: adr/0007 (propagate
resets through the parallel fold) and adr/0020 (reset at the turn boundary,
not per call).
Once the pages exist: every PR that changes behaviour, structure, a risk or a
decision updates them in the SAME PR, and a merge is not finished until they
describe main as it now is.
Running the tests
There is no database. Skip every DB and partition-setup step in the global
rules. The suite still needs MIX_TEST_PARTITION set, because config/test.exs
derives :web_dir from it to isolate the session store between concurrent runs:
MIX_TEST_PARTITION=_issue_<num> mix test
Omitting it makes two concurrent runs share one web session directory, which fails in ways that look like flakes but are not.
Known failures that are not yours
Measured 2026-09-13 on main (5db70d8). Do not chase these:
- 3 symlink-canonicalisation tests in
ExAthena.ToolContextTest. - 1
ExAthena.Tools.BashTestconfinement test, "writes inside a root succeed". NOT a missingbwrap— the binary is on PATH here (/usr/bin/bwrap, 0.8.0) and the test still fails. It cannot create a user namespace inside the dev container:bwrap --dev-bind / / trueexits 1 with "No permissions to create new namespace".ExAthena.Sandbox.available?/1only checks that the helper exists, so the confined path runs, every command under it fails, and the write never lands. Run that one-liner before believing any other explanation. ExAthena.Tools.AskUserTestflakes intermittently.- The LSP /
ImplicitDiagnosticsfamily flakes in CI; re-run the job once before treating a failure there as real.
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 Changed · +1 lines · +2 tokens per session 025139f0f187
- 4d ago Changed · +7 lines · +126 tokens per session a6f27d4f1fbc
- 5d ago First seen · 90 lines · 1,000 tokens per session scan A e82078c8c32d
ex_athena CLAUDE.md is an instructions file published in the GitHub repository udin-io/ex_athena (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,128 tokens to every session, about $0.0056 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 2026-09-13.
Other instructions, from other repositories
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).
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.
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.
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.
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).