oraclemcp AGENTS.md

oraclemcp AGENTS.md is an instructions file for Codex, OpenCode from MuhDur/oraclemcp. It costs 4,176 tokens per session, scanned C, original, Apache-2.0.

Repository instructions for oraclemcp, an unofficial Rust server that lets agents work with Oracle databases through MCP.

In plain words
What is it for?
They guide Rust development across the workspace's library crates and binary, optional PL/SQL support, safe agent collaboration, and release-related decisions.
Why use it?
They set strict safety rules for file deletion and irreversible actions while defining the project's workspace and verification practices.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/muhdur/oraclemcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/MuhDur/oraclemcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for oraclemcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/muhdur/oraclemcp/agents-md.svg)](https://agentmods.dev/instructions/muhdur/oraclemcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/muhdur/oraclemcp/agents-md"><img src="https://agentmods.dev/badge/instructions/muhdur/oraclemcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,176 This file is loaded in full into every session.
When invoked 4,176 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.04176 $0.04176
Opus 5 $0.02088 $0.02088
Sonnet 5 $0.00835 $0.00835
Haiku 4.5 $0.00418 $0.00418

Measured 4d ago against content hash daf4367461d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

oraclemcp AGENTS.md scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

deletion, or `rm -rf` on tracked paths without explicit in-session approval.
AGENTS.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - oraclemcp

Operating rules for agents working in this repository.

oraclemcp is an unofficial, engine-free, safe-by-default Oracle Database MCP server in pure Rust: a small Cargo workspace of 9 oraclemcp-* library crates plus the oraclemcp binary. Its optional plsql-intelligence feature embeds the PL/SQL engine for offline tools; the separate plsql-mcp server is deprecated. Independent open-source project; not affiliated with Oracle.

RULE 1 - ABSOLUTE

Do not delete any file or directory unless the operator gives the exact command in-session. This includes files you just created. If something should go, stop and ask first.

Irreversible / outward-facing actions

Never run git reset --hard, git clean -fd, git push --force, branch deletion, or rm -rf on tracked paths without explicit in-session approval. Never force-push main. Do not commit on the operator's behalf without a clear in-session go-ahead. crates.io publishes and registry listings are permanent (versions immutable, names claimed forever); treat publishing as a gated, deliberate step.

Swarm operating constitution

Eighteen rules. Rules 1-12 were mined from the 2026-07 multi-repo swarm retrospective (docs/plan/RETRO_SWARM_CAMPAIGN_2026-07.md §3G, docs/plan/PLAN_ENGINEERING_PROGRAM.md §27.3); rules 13-17 were mined from the 2026-07-21 five-agent session, one per incident it produced (rule 18 from an incident during the session that encoded the others). Binding on every agent in this repo, solo or swarmed — most are new; a few name-and-link existing rules above so the constitution stays the one place to check:

  1. Never defer planned work on your own initiative — deferral is the operator's call, not an agent's judgment call.
  2. Green means honestly green; surface red before the operator finds it.
  3. Claims must be evidence-backed — never assert what you haven't just run and checked.
  4. Reread this file (and README.md) until understood, every session, before acting.
  5. Think before acting ("ultrathink"): verify, then execute — don't patch on a hunch.
  6. Be resource-disciplined: don't trash the host, the disk, or the token/session budget (CARGO_BUILD_JOBS caps, scoped -p builds over full-workspace ones, no unbounded concurrent compiles).
  7. Keep driving autonomously, but follow explicit operator choices — model, agent freshness, scope — exactly; deviation is the fastest path to anger.
  8. The fail-closed guard is sacred and tighten-only — see "The safety invariant" below; this rule doesn't restate it, it just makes the constitution complete.
  9. Confidentiality is absolute: field-test/live-customer identifiers never leave quarantine (todelete/, gitignored) or enter a committed artifact.
  10. No surprise costs — cloud resources (OCI, etc.) stay free-tier; a hard rule, not a target.
  11. Land complete, not sliced across version bumps or half-shipped across sessions.
  12. Escalate blockers to the operator; delegate unforeseen work to the tracker (br create), don't quietly derail the authoritative prompt's scope.
  13. A modified file that is not yours is another agent mid-edit, not a defect. Check git status on a file before declaring it broken, and judge the committed truth (git show HEAD:<path>) before filing a build blocker or going idle on one.
  14. Close evidence comes from a tree verified clean of other agents' work. Derive the evidence source block from git rather than asserting it; commit your in-scope work first, and generate a whole-tree reproducibility proof from a dedicated clean worktree at HEAD.
  15. Read the gate verdict yourself; never infer a pass from a successful push. git push reports what the remote accepted, not what the gate decided. A gate that printed a failure is a failure no matter how the push went.
  16. Never block a turn on an unbounded wait. Check once, report, move on. Every wait carries a deadline, and reaching the deadline is a result to report — not a reason to wait again. A blocked turn queues every dispatch behind it.
  17. A struct field and its initializers are ONE logical change, landed in ONE commit by ONE agent. The same holds for any edit whose halves do not compile apart: a git mv and its references, a trait method and its impls, an enum variant and its exhaustive matches. Split it across panes and you break the build for everyone in the shared checkout.
  18. Commit explicit paths, then verify what landed. git commit -- <path>... and git show --stat HEAD; never -a/git add -A in a shared checkout. A deletion of a path that still exists in the worktree is a stale index snapshot committed over someone else's landed work, not a delete.

Read the full file on GitHub · 314 lines

Changes

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.

  1. 4d ago First seen · 314 lines · 4,176 tokens per session scan C daf4367461d4

Subscribe to this mod's changes

oraclemcp AGENTS.md is an instructions file published in the GitHub repository MuhDur/oraclemcp (3 stars, last pushed 11d ago), licensed Apache-2.0. It adds 4,176 tokens to every session, about $0.0209 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories