codexa-brief

A command that creates a focused brief for a coding task and the changes already made in the current working folder.

In plain words
What is it for?
Use it to review likely impact, risks, tests, freshness, relevant files, and suggested next tools before editing.
Why use it?
It helps when the task’s scope is unclear or existing changes make it harder to know what to read and change first.

Command

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 commands/mirnoorata/codexa/codexa-brief
Clone the repo
git clone --depth 1 https://github.com/mirnoorata/codexa
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00015 $0.00170
Opus 5 $0.00008 $0.00085
Sonnet 5 $0.00003 $0.00034
Haiku 4.5 $0.00002 $0.00017

Measured 2d ago against content hash 0c53359995a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexa-brief 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.

integrations/claude-code/commands/codexa-brief.md · 17 lines

What it actually says

Ask Codexa for a focused task brief when the scope is ambiguous or the dirty tree needs Codexa-ranked read-first guidance. Skip this command when direct source evidence already makes a bounded local task clear; for an exact non-trivial edit, go directly to the saved change plan. The brief bundles impact, risks, covering tests, freshness, read-first files, relationship evidence where available, quality signals, and structured nextTools for the stated task plus the existing dirty diff.

!bash "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/brief.sh" "$ARGUMENTS"

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. 2d ago First seen · 17 lines · 15 tokens per session scan A 0c53359995a2

Subscribe to this mod's changes

codexa-brief is a command published in the GitHub repository mirnoorata/codexa (2 stars, last pushed 29d ago), licensed MIT. It adds 15 tokens to every session and 170 once invoked, about $0.0001 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.