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/zaimwa9/themis/agents-mdgit clone --depth 1 https://github.com/Zaimwa9/themisWrote 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/zaimwa9/themis/agents-md)<a href="https://agentmods.dev/instructions/zaimwa9/themis/agents-md"><img src="https://agentmods.dev/badge/instructions/zaimwa9/themis/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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
themis 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 3d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Themis — agent guide
Self-hosted GitHub PR review bot. FastAPI controller + credential-isolated
agent service, in-memory job queue, engine adapters over agent CLIs
(codex, claude, glm). No database, no broker.
Commands
uv sync --locked # install deps (Python 3.12, uv)
uv run pytest -q # test suite
uv run ruff check src tests
uv run python -m themis # run locally (reads THEMIS_* env)
CI runs exactly pytest and ruff; both must pass.
Layout
src/themis/app.py— FastAPI app factory, startup (webhook self-registration)src/themis/router.py— webhook + API routes; events become queue jobssrc/themis/action.py— GitHub Actions entrypoint (action.ymlat the repo root); one event, one synchronous job, staticGITHUB_TOKENsrc/themis/events.py— webhook payload parsing, trigger decisionssrc/themis/queue.py— in-memory queue, one worker, dedupsrc/themis/review_service.py— review pipeline: clone, engine run, parse, postsrc/themis/engines/— engine adapters over a hardened subprocess runner (base.py: env allowlist, process-group kill, quota detection);__init__.pyis the registrysrc/themis/github/— App auth (JWT, installation tokens), REST/GraphQL clientsrc/themis/security.py— outbound redaction of secretssrc/themis/prompts.py/output.py— prompt builders / agent output parsingsrc/themis/workspace.py— shallow clone, token scrub, cleanupsrc/themis/config.py—THEMIS_*env settings + per-repo.themis/config.yamltests/— mirrorssrc/themis/, one test file per module, pytest-asyncio
Rules
- Conventional Commits; release-please derives versions and the changelog from commit messages.
- Behavior changes ship with tests in the mirrored
tests/test_<module>.py; bug fixes ship a regression test that fails without the fix. - Every string that ends up on GitHub passes
redact_outbound(src/themis/security.py). A new posting path without it is a blocker. Agent-written bodies (summaries, findings, replies) usesanitize_agent_textinstead: it also defangs<!-- themis:... -->markers, which themis reads back off GitHub as control decisions. Only controller-authored constants may carry a real marker. - Engine subprocesses receive
allowlisted_envonly, neveros.environ. - Per-repo config parsing is lenient: invalid values degrade to defaults with a warning, never a crash.
- User-facing config changes (env vars,
.themis/config.yamlkeys) updateREADME.mdanddocs/configuration.mdin the same PR. - Engines are siblings: a guard or edge case added to one engine is checked against the others.
- Log lines use
themis_<event>snake_case with key=value pairs, never secret values. - No new runtime dependencies without a stated reason; the one-container, no-external-services shape is a feature.
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.
- 3d ago First seen · 69 lines · 868 tokens per session scan A 76eccb1a9817
themis AGENTS.md is an instructions file published in the GitHub repository Zaimwa9/themis (11 stars, last pushed 1mo ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.