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/mirnoorata/codexa/agents-mdgit clone --depth 1 https://github.com/mirnoorata/codexaWhat 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 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
codexa 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codexa Project Kernel
Keep this automatic layer repository-local and compact. Detailed setup,
recovery, architecture, and release procedures live in README.md and
docs/; load them only when the task reaches that boundary.
Development
- Restore locked dependencies with
npm ci; usenpm installonly when deliberately changing dependencies andpackage-lock.json. - Run
npm run checkfor the normal full gate. - Keep generated or host-local state out of Git:
dist/,node_modules/,.codex/codebase/,.codex/cache/, local storage, config, and hooks are ignored. The tracked environment and bootstrap launchers are intentional. - Use deterministic public fixtures and placeholders such as
/path/to/project,OWNER/REPO, andexample.com. Do not commit private paths, projects, hosts, credentials, logs, or session memory.
Project Startup
- In the desktop Codex composer, select this saved project,
Worktree, the intended starting branch, and the Codexa local environment before the first prompt. Mobile remote access may continue that chat but does not configure its local setup. - Adopt the app-created linked worktree; never create a second checkout for the same task. Attach a named branch before committing if the app starts detached, and leave app-managed cleanup to the app.
- The tracked Bash and PowerShell launchers delegate to one serialized Node
bootstrap. Generate dependencies, build output,
corewiring, and the index in the active worktree; never copy machine-local config, hooks, indexes, or absolute launch commands from another checkout. - Setup proof is the immutable blob behind the per-worktree
refs/worktree/codexa/bootstrap-receiptref. SessionStart validates its durable subset;worktree-receipt validate --scope adoptionadditionally binds generated runtime/dependencies for a trusted shared controller, and the defaultfullscope is the completion gate. A receipt never authorizes executing unvalidated worktree output. - Missing, stale, or invalid setup evidence is source-ready, not edit-ready.
Follow README
Codex Project Worktrees And Local Setupfor repair. Neither config nor a receipt proves current-thread MCP activation.
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 First seen · 53 lines · 629 tokens per session scan A d52d760c11cf
codexa AGENTS.md is an instructions file published in the GitHub repository mirnoorata/codexa (2 stars, last pushed 29d ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
Ctxo CLAUDE.md
Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
Ctxo copilot-instructions.md
Instructions for alperhankendi/Ctxo, covering ctxo mcp tool usage (mandatory), before any code modification, before starting a task, before reviewing a pr or diff and when exploring or searching code.
cartograph AGENTS.md
Instructions for adder-factory/cartograph, covering existing project rule, architecture and hard requirements, step 0 — install the binary, step 1 — choose database ownership and managed local database (macos/linux).
rs-agent-code-utility AGENTS.md
AGENTS.md instructions for njfio/rs-agent-code-utility, covering repository guidelines, tooling: use the rts index, not grep / rg, when to use which tool, verify before you claim and two cli shapes.
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
martin-loop AGENTS.md
Instructions for Keesan12/martin-loop, covering martinloop agent operating rules, repository authority, mandatory internal-first sequence, prohibited actions and required internal health proof.