Borrowing it
Nothing to install: this file belongs to MuhDur/oraclemcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MuhDur/oraclemcp/main/AGENTS.mdgit clone --depth 1 https://github.com/MuhDur/oraclemcpWrote 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/muhdur/oraclemcp/agents-md)<a href="https://agentmods.dev/instructions/muhdur/oraclemcp/agents-md"><img src="https://agentmods.dev/badge/instructions/muhdur/oraclemcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/muhdur/oraclemcp/agents-md"><img src="https://agentmods.dev/badge/instructions/muhdur/oraclemcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03892 | $0.03892 |
| Opus 5.5 | $0.01557 | $0.01557 |
| Sonnet 5.5 | $0.00778 | $0.00778 |
| Haiku 4.5 | $0.00389 | $0.00389 |
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 8d 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. How it starts
The opening of the file, as written. The whole thing — 299 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, safe-by-default Oracle Database
MCP server in pure Rust: a small Cargo
workspace of 9 engine-free oraclemcp-* library crates plus the oraclemcp
binary. Release archives, the single ghcr.io/muhdur/oraclemcp image, and the
default source build embed the plsql-intelligence engine for offline tools;
custom --no-default-features builds omit it. The maintained primary driver is
oraclemcp-driver-cx, with a bounded official oracledb connect-time alternate
for compatible password connections. The SQL guard remains independent of
the PL/SQL engine. 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.
Working rules
Binding on every agent, solo or swarmed. They come from past incidents
(docs/plan/RETRO_SWARM_2026-10-04.md, docs/plan/SWARM_RECAP_2026-10.md).
- Never defer planned work on your own initiative; deferral is the operator's call.
- Green means honestly green. Surface red before the operator finds it.
- Claim only what you have just run and checked.
- Follow explicit operator choices (model, scope, agent count) exactly.
- The fail-closed guard is sacred and tighten-only (see "The safety invariant").
- Confidentiality: field-test/live-customer identifiers never leave
todelete/(gitignored) or enter a committed artifact. - No surprise costs: cloud resources (OCI etc.) stay free-tier.
- Be resource-disciplined: scoped
-pbuilds, a per-agent target dir, no unbounded concurrent compiles. - A modified file that is not yours is another agent mid-edit, not a defect.
Check
git status/git show HEAD:<path>before calling it broken. - Commit explicit paths (
git commit -- <path>...), then check what landed withgit show --stat HEAD. Never-a,git add -Aor--amendin the shared checkout. A struct field and its initializers (or a trait method and its impls, an enum variant and its matches) land in one commit. - Never block a turn on an unbounded wait. Check once, report, move on.
- Escalate blockers to the operator; file unforeseen work with
br createinstead of quietly widening scope.
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.
- 8d ago Changed · -11 lines · -201 tokens per session c899ae762f11
- 9d ago Changed · -72 lines · -1,015 tokens per session 3e47c8815666
- 1mo ago Changed · +29 lines · +430 tokens per session c16d88b3badd
- 1mo ago Changed · +1 lines · +19 tokens per session 0b3d28ba758d
- 1mo ago Changed · +38 lines · +483 tokens per session 4d272c8cc8ec
- 2mo ago First seen · 314 lines · 4,176 tokens per session scan C daf4367461d4
oraclemcp AGENTS.md is an instructions file published in the GitHub repository MuhDur/oraclemcp (4 stars, last pushed today), licensed Apache-2.0. It adds 3,892 tokens to every session, about $0.0156 per session on Opus 5.5. 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.
oraclemcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oraclemcp AGENTS.mdMuhDur/oraclemcp | Instructions file | 4 | today | Apache-2.0 | C | 3,892 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |