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/osaurus-ai/osaurus/agents-mdgit clone --depth 1 https://github.com/osaurus-ai/osaurusWrote 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/osaurus-ai/osaurus/agents-md)<a href="https://agentmods.dev/instructions/osaurus-ai/osaurus/agents-md"><img src="https://agentmods.dev/badge/instructions/osaurus-ai/osaurus/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 | $0.02723 | $0.02723 |
| Opus 5 | $0.01362 | $0.01362 |
| Sonnet 5 | $0.00545 | $0.00545 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
osaurus 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Configuration - osaurus-staging
See ~/AGENTS.md for the global Codex environment, wiki protocol, hard rules,
machine context, and useful commands.
Build & Test
Running tests and builds is encouraged — they're how we keep quality high. The
canonical lanes live in Makefile:
make test—swift test --package-path Packages/OsaurusCore(fast unit loop).make ci-test— mirrors the CItest-corexcodebuild job (xcbeautifyoutput, xcresult bundle atbuild/Tests.xcresult).make cli/make app— build the CLI and the embedded app viaxcodebuildagainstosaurus.xcworkspace.make evals/make evals-all— run OsaurusEvals suites underPackages/OsaurusEvals/Suites/*.- Live-app smoke:
scripts/live-proof/launch-keychain-free-osaurus.sh.
Keychain tip (optional)
Some tests touch Osaurus Keychain wrappers. If a test doesn't need real Keychain access, prefer running it in keychain-disabled mode to avoid unrelated "wants to use your confidential information" prompts:
OSAURUS_DISABLE_KEYCHAIN_FOR_TESTS=1 \
OSAURUS_TEST_ROOT=/tmp/osaurus-test \
OSU_MODELS_DIR=/tmp/osaurus-test-models \
make test
In that mode, Keychain wrappers should return nil / no-op on reads, writes,
and deletes rather than calling SecItemCopyMatching / SecItemAdd /
SecItemUpdate / SecItemDelete against the login Keychain.
OSU_MODELS_DIR (pointed at an empty dir) matters on machines with real
models in ~/MLXModels: dispatch-style tests start real ChatSession.send
turns, and without the override they resolve the user's installed models and
try to load them inside the SwiftPM harness — which has no Metal kernels and
dies with MLX/MLXArray.swift precondition failed. With the override those
sends fail fast with modelUnavailable, matching CI behavior. Keychain-gated
suites (e.g. PluginAgentScopingTests) still fail by design under
OSAURUS_DISABLE_KEYCHAIN_FOR_TESTS=1; run those without the flag when you
need real Keychain proof.
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 · 195 lines · 2,723 tokens per session scan A d3c8d72c77cc
osaurus AGENTS.md is an instructions file published in the GitHub repository osaurus-ai/osaurus (7,756 stars, last pushed yesterday), licensed MIT. It adds 2,723 tokens to every session, about $0.0136 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
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.
TMDb CLAUDE.md
Instructions for adamayoung/TMDb, covering claude.md, project overview, topic docs, knowledge base and development workflow.
swift-secp256k1 AGENTS.md
Instructions for 21-DOT-DEV/swift-secp256k1, covering agents.md (swift-secp256k1), commands, non-obvious patterns, code style and boundaries.
swift-tui AGENTS.md
Instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.
starboard CLAUDE.md
Instructions for palamim/starboard, covering claude.md, commands, code style, architecture and non-obvious gotchas (not discoverable by reading the code).
Swift-Testing-Agent-Skill copilot-instructions.md
Instructions for AvdLee/Swift-Testing-Agent-Skill, covering core agent skills principles, format compliance, skill content organization (progressive disclosure), review focus areas and common issues to flag.