director:refresh

A command for refreshing a project's stored context by scanning its source code again, with an optional second pass for research.

In plain words
What is it for?
Use it to rescan the codebase, optionally refresh research as well, and check whether the project has the files and setup needed for analysis.
Why use it?
It keeps project information current after code changes and warns when the project has not been set up or contains no code to analyze.

Skill for Claude CodeCodex

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 skills/noahrasheta/director/refresh
Any agent
npx skills add noahrasheta/director --skill refresh
Clone the repo
git clone --depth 1 https://github.com/noahrasheta/director

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,493 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 $0.00022 $0.03493
Opus 5 $0.00011 $0.01747
Sonnet 5 $0.00004 $0.00699
Haiku 4.5 $0.00002 $0.00349

Measured yesterday against content hash 9c06da8206a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

director: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 yesterday.

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.

skills/refresh/SKILL.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Director Refresh

First, check if .director/ exists. If it does not, say:

"No project set up yet. Run /director:onboard to get started."

Stop here if no .director/ exists.


Check Project State

Verify source files exist beyond .director/. Check for: package.json, requirements.txt, go.mod, Cargo.toml, Gemfile, src/, app/, lib/, pages/, or common source files (.ts, .tsx, .js, .jsx, .py, .rb, .go, .rs, .java, .swift, .vue, .svelte).

If no source files exist:

"I don't see any code to analyze. If you've added code since setting up, make sure it's in the project root."

Stop here.


Determine Refresh Scope

Check $ARGUMENTS for research-related terms. If arguments contain "research", "everything", "all", or "full": scope = FULL (codebase + research). Otherwise: scope = CODEBASE_ONLY.


Soft Guard for Research Without Vision

If scope is FULL, read .director/VISION.md. Check if it has only placeholder text (> This file will be populated when you run /director:onboard, headings with no substantive content, or _What are you calling this project?_ style markers).

If VISION.md has only placeholder text:

"Your vision isn't set up yet, so research results may be generic. Want to continue anyway?"

Wait for response. If they decline, switch scope to CODEBASE_ONLY and continue.


Save Current State for Comparison

BEFORE running any pipelines, read the existing summary files so you can compare later:

  1. Read .director/codebase/SUMMARY.md if it exists. Store contents as baseline. If file does not exist, this is a first-time scan (present findings instead of a diff).
  2. If scope is FULL: also read .director/research/SUMMARY.md if it exists. Store as baseline.

Codebase Mapping Pipeline

"Scanning your codebase..."

Codebase Size Assessment

find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" -o -name "*.py" -o -name "*.rb" -o -name "*.go" -o -name "*.rs" -o -name "*.java" -o -name "*.swift" -o -name "*.vue" -o -name "*.svelte" \) -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/.director/*" -not -path "*/vendor/*" -not -path "*/dist/*" -not -path "*/build/*" | wc -l

Read the full file on GitHub · 375 lines

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. yesterday First seen · 375 lines · 22 tokens per session scan A 9c06da8206a8

Subscribe to this mod's changes

director:refresh is a skill published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 3,493 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.