Borrowing it
Nothing to install: this file belongs to Averyy/codex-dobby-mcp. 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/Averyy/codex-dobby-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Averyy/codex-dobby-mcpWrote 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/averyy/codex-dobby-mcp/agents-md)<a href="https://agentmods.dev/instructions/averyy/codex-dobby-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/averyy/codex-dobby-mcp/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/averyy/codex-dobby-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/averyy/codex-dobby-mcp/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 | $0.01987 | $0.01987 |
| Opus 5.5 | $0.00795 | $0.00795 |
| Sonnet 5.5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
codex-dobby-mcp 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 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.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository and Dobby usage guidance
Working on this repository
- Use
uvfor dependency management and run Python commands throughuv run. - Preserve unrelated worktree changes. The repository may intentionally be dirty while Dobby reviews it.
- Run the focused tests for changed code, then
uv run pytestbefore handing off a runtime change. - Keep
README.md, MCP tool descriptions, schemas, prompts, and tests synchronized when changing a public request or response contract.
Mutation testing
The suite's strength is scored by scripts/mutation_test.py: it flips one
executed comparison, boolean operator, not, or bool constant at a time, and
some test must fail. The recorded full-sweep baseline lives in
scripts/mutation_baseline.json; survivors listed there are expected, and the
subset proven semantically unkillable is documented in TODO.md under
"Known-equivalent mutants". Both tools snapshot the exact working tree —
uncommitted changes included — into throwaway git worktrees and never modify
the real checkout.
- One-time setup:
uv sync --group mutation(addscoverage). - Changed lines only, what CI runs on every pull request:
uv run python scripts/mutation_test.py sweep --since origin/main --check - Full sweep (roughly half an hour; CI repeats it weekly via
mutation-sweep.yml):uv run python scripts/mutation_test.py sweep --check - Refresh the recorded baseline after a full sweep — never from a
--sincerun:uv run python scripts/mutation_test.py sweep --update-baseline - Prove that named tests kill hand-written mutations:
uv run python scripts/mutation_test.py verify spec.json tests/test_file.py, wherespec.jsonis a JSON list of{"file", "line", "new", "label"}objects (file is a basename undersrc/codex_dobby_mcp).
A new survivor on lines you changed fails the CI lane: add a test that kills it, or — only if the mutant is provably equivalent — add the proof to TODO.md and refresh the baseline in the same change. Baseline matching keys on the survivor's source-line text, not its line number, so refactors that move known-weak lines do not fail the lane, while edits that rewrite one do.
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.
- 4d ago First seen · 66 lines · 1,987 tokens per session scan A 1bc5947c4e4f
codex-dobby-mcp AGENTS.md is an instructions file published in the GitHub repository Averyy/codex-dobby-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 1,987 tokens to every session, about $0.0079 per session on Opus 5.5. 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 2026-10-26.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.