brief-refresh

A command that audits project documentation against the current source code and records contradictions, outdated assumptions, missing documentation, and possible improvements.

In plain words
What is it for?
Use it to create a timestamped audit, suggest architecture decisions and features, open labeled GitHub issues, and commit the audit through a branch and self-merged pull request.
Why use it?
It finds places where docs and code have drifted apart, including decisions made in code but not written down.

Command for Claude Code

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/nkhdiscovery/headless-agentic-codebase/brief-refresh
Clone the repo
git clone --depth 1 https://github.com/nkhdiscovery/headless-agentic-codebase

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 226 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 $0.00012 $0.00226
Opus 5 $0.00006 $0.00113
Sonnet 5 $0.00002 $0.00045
Haiku 4.5 $0.00001 $0.00023

Measured 2d ago against content hash 4b0a1dc31420, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brief-refresh 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.

.claude/commands/brief-refresh.md · 28 lines

What it actually says

Audit the project docs and current state.

  1. Read every file in docs/ including ADRs.
  2. Scan source code for actual current state.
  3. Write docs/audits/$(date +%Y-%m-%d-%H%M).md with sections:

Contradictions — file:line, what doc says, what code shows.

Stale assumptions — claims that were true but aren't now.

Quietly resolved open decisions — items in product.md that have been decided in code but not written down.

Doc gaps — patterns that recur in code but aren't documented. Candidates for new ADRs.

Refactoring opportunities — worth >1hr saved future work.

New feature ideas — what would make the project meaningfully better.

For each finding:

  • Clear-cut → file GitHub issue with agent-proposed + priority:low.
  • Judgment-call → file with needs-decision.

Commit audit file via branch + self-merge.

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 · 28 lines · 12 tokens per session scan A 4b0a1dc31420

Subscribe to this mod's changes

brief-refresh is a command published in the GitHub repository nkhdiscovery/headless-agentic-codebase (10 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 226 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.