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/floci-io/floci-oci/agents-mdgit clone --depth 1 https://github.com/floci-io/floci-ociWrote 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/floci-io/floci-oci/agents-md)<a href="https://agentmods.dev/instructions/floci-io/floci-oci/agents-md"><img src="https://agentmods.dev/badge/instructions/floci-io/floci-oci/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 | $0.02516 | $0.02516 |
| Opus 5 | $0.01258 | $0.01258 |
| Sonnet 5 | $0.00503 | $0.00503 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade A, and why
floci-oci 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 2d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide: floci-oci
Guidance for AI coding agents working in the floci-oci repository.
Project Overview
floci-oci is a Java-based local Oracle Cloud Infrastructure (OCI) emulator built on Quarkus. Its goal is full OCI SDK and OCI CLI compatibility through real OCI wire protocols, not convenience APIs. It is the OCI sibling of floci (AWS, port 4566), floci-az (Azure, 4577) and floci-gcp (GCP, 4588).
- Port: 4599
- Stack: Java 25, Quarkus, JUnit 5, RestAssured, Jackson
- Package root:
io.floci.oci - Config prefix:
floci-oci.*/ envFLOCI_OCI_*
First Principles
- Preserve OCI protocol compatibility
- Match OCI SDK and CLI behavior
- Reuse existing patterns
- Prefer correctness over convenience
- Keep changes narrow and testable
Critical rules:
- Do not introduce custom endpoint shapes
- Do not change request or response formats for convenience
- Never invent protocol behavior: consult the reference sources under
local/oracle/(see "OCI Source as Reference" below;make refsdownloads them)
Architecture
Layered: Controller (JAX-RS, parses OCI REST input) → Service (business logic, throws
OciException) → Model (model/Stored*.java, @RegisterForReflection).
Core infrastructure (io.floci.oci.*):
config/EmulatorConfig: single@ConfigMapping(prefix = "floci-oci")interfacecore/common/:OciException+OciExceptionMapper(error shape{"code":"...","message":"..."}+opc-request-idheader),ServiceRegistry+ServiceDescriptor(self-registering),ServiceEnabledFilter(503 for disabled services),RequestContext(tenancy/user/region)core/storage/:StorageBackend(memory/persistent/hybrid/wal viaStorageFactory),TenancyAwareStorageBackend(keys prefixed by tenancy OCID)core/common/docker/: sidecar container managementlifecycle/:EmulatorLifecycle, init hooks,/health+/_floci-oci/*endpoints
OCI Protocol Rules
- Every service except Object Storage uses a date-versioned path prefix
(Identity
/20160918/…); Object Storage uses/n/{namespace}/b/{bucket}/o/{object}. JAX-RS@Pathmatching dispatches directly: there is no routing filter. - Errors:
{"code": "...", "message": "..."}body + correct HTTP status. 404 isNotAuthorizedOrNotFound(OCI deliberately conflates the two). - Every response carries an
opc-request-idheader. - Pagination:
limit/pagequery params in,opc-next-pageresponse header out. Some list APIs return a bare JSON array: verify each against the SDK model. - OCIDs:
ocid1.<type>.<realm>.<region>.<unique>(region omitted for global resources). - Auth: the
Authorization: Signature …header is parsed for tenancy/user context only; the RSA signature is never verified. - Tenancy is the storage partition; compartment is a field on each resource filtered
via
?compartmentId=. Do not conflate them. - Async operations return 202 +
opc-work-request-idand are polled via work requests.
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.
- 2d ago Changed · +4 lines · +17 tokens per session 26b91a5206c1
- 6d ago First seen · 204 lines · 2,499 tokens per session scan A e07e9ffa6c9a
floci-oci AGENTS.md is an instructions file published in the GitHub repository floci-io/floci-oci (63 stars, last pushed 3d ago), licensed MIT. It adds 2,516 tokens to every session, about $0.0126 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
meme-search CLAUDE.md
Instructions for neonwatty/meme-search, covering claude.md, 📁 file organization guidelines, 🤖 task agent usage guidelines, when to use task agents and documentation lookup pattern.
SForum AGENTS.md
AGENTS.md instructions for zhuchunshu/SForum, covering agent guide, project intent, working principles, stack and directory map and commands.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
redd-archiver CLAUDE.md
Instructions for 19-84/redd-archiver, covering claude.md, project overview, deviations from global standards, build & run commands and docker development (primary method).