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.
npx agentmods add instructions/juyterman1000/entroly/agents-mdgit clone --depth 1 https://github.com/juyterman1000/entrolyWrote 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/juyterman1000/entroly/agents-md)<a href="https://agentmods.dev/instructions/juyterman1000/entroly/agents-md"><img src="https://agentmods.dev/badge/instructions/juyterman1000/entroly/agents-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 | $0.00616 | $0.00616 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
entroly AGENTS.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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is configured for OpenAI Codex CLI and other agentic coding tools.
Use gstack with Codex
When gstack is installed for Codex, use the gstack workflow for non-trivial Entroly changes:
/office-hours -> /plan-ceo-review -> /plan-eng-review -> implement -> /review -> /qa or targeted tests -> /ship -> /retro
Install gstack for Codex with:
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
cd ~/gstack
./setup --host codex
This installs gstack skills under ~/.codex/skills/gstack-*/.
Entroly operating rule
Entroly is an auditable context-control plane. Optimize for trust before speed:
- preserve receipt honesty
- preserve reversible context compression
- keep WITNESS / RAVS fail-closed
- avoid surprise remote calls
- keep prompt/cache prefixes stable unless intentionally changed
- keep Python, Rust, WASM, npm, Homebrew, docs, and native-status versions aligned
- never make savings or quality claims without baseline, token budget, workload, and caveats
Default Codex workflow
For any meaningful change:
- Define the smallest useful user-facing improvement.
- Write a short plan before editing.
- Identify affected surfaces: selection, receipts, WITNESS, RAVS, proxy, CLI, packaging, docs, or release.
- Make the smallest safe patch.
- Run targeted tests first.
- Expand to release tests only if packaging/native/release surfaces changed.
- Summarize risk, test evidence, and rollback path.
UI Verification Rule
For any pull request or change that modifies UI state (entroly dashboard, web UI assets, or interactive docs):
- Include a short video recording or visual demo (e.g., WebP/MP4 recording) in the PR description demonstrating the UI flow and verifying no visual regressions.
Commands
pip install -e ".[full]"
pytest tests/ -v --tb=short --timeout=60
ruff check entroly/
python tests/functional_test.py
Rust/native changes:
# maturin must run from entroly-core/ — Cargo.toml is not at the repo root.
cd entroly-core && maturin develop --release
cd entroly-core && cargo test --lib
cd entroly-core && cargo clippy --all-targets -- -D warnings
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.
- 6d ago First seen · 82 lines · 616 tokens per session scan A c177b29e45a6
entroly AGENTS.md is an instructions file published in the GitHub repository juyterman1000/entroly (443 stars, last pushed yesterday), licensed Apache-2.0. It adds 616 tokens to every session, about $0.0031 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.
Other instructions, from other repositories
lean-ctx AGENTS.md
AGENTS.md instructions for yvgude/lean-ctx, covering context engineering layer, mandatory multi-agent delivery, integration mode: replace, subagent compatibility (cursor / claude code) and cli commands (optimized shell, lower overhead).
lean-ctx copilot-instructions.md
Copilot instructions for yvgude/lean-ctx, a project described as: Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens…
fish-bridge-mcp copilot-instructions.md
Instructions for MakeaMouse/fish-bridge-mcp, a project described as: An economical and fuel(token) efficient AI tool, graph session memory for looong chat session.
knitbrain CLAUDE.md
Instructions for PDgit12/knitbrain, covering knitbrain, session start, tool surface highlights (37 tools), project map and build gates.
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).