speckit.spex-detach.detach

speckit.spex-detach.detach is a command for Claude Code from rhuss/cc-spex. It costs 16 tokens per session (668 once invoked), scanned A, original, Apache-2.0.

A command for hiding or archiving specification files when contributing to an upstream project. Its stealth mode adds paths to Git’s local exclude file without changing committed files.

In plain words
What is it for?
It helps enable or check stealth mode and copy specification artifacts to a configured neighboring repository for archiving.
Why use it?
It keeps local specification artifacts out of normal Git changes while allowing them to remain on the developer’s machine.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the spex plugin — 1 skill, 7 commands shipped together

Good fit It helps enable or check stealth mode and copy specification artifacts to a configured neighboring repository for archiving.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rhuss/cc-spex/speckit.spex-detach.detach
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.

Clone the repo
git clone --depth 1 https://github.com/rhuss/cc-spex

Made for: Claude Code.

Or install spex, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

Wrote 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.

agentmods badge for speckit.spex-detach.detach

README.md
[![agentmods](https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-detach.detach/github.svg)](https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-detach.detach)
Your own site
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-detach.detach"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-detach.detach/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.

agentmods 80×15 button for speckit.spex-detach.detach

Your own site · 80×15
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-detach.detach"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-detach.detach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00668
Opus 5 $0.00008 $0.00334
Sonnet 5 $0.00003 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 11d ago against content hash a4852be7d96e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speckit.spex-detach.detach 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 11d 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.

spex/extensions/spex-detach/commands/speckit.spex-detach.detach.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spex Detach

Manage spec artifact visibility for upstream contributions. Stealth mode uses .git/info/exclude to hide spec files from git without modifying any committed files.

Subcommands

  • enable (default): Write .git/info/exclude entries to hide spec artifacts from git
  • archive: Copy spec artifacts to the configured project-specs sibling repo
  • is-enabled: Check if the detach extension is active (exit 0 = yes, exit 1 = no)

Execution

Run the spex-detach.sh script:

DETACH_SCRIPT=".specify/extensions/spex-detach/scripts/spex-detach.sh"
[ -x "$DETACH_SCRIPT" ] || { echo "ERROR: spex-detach.sh not found"; exit 1; }

Subcommand: enable

Write configured exclude paths to .git/info/exclude. Idempotent, preserves existing entries, warns if spec files are already tracked.

RESULT=$("$DETACH_SCRIPT" enable)
EXIT_CODE=$?

if [ "$EXIT_CODE" -eq 0 ]; then
  ADDED=$(echo "$RESULT" | jq -r '.paths_added | length')
  ALREADY=$(echo "$RESULT" | jq -r '.already_present')
  if [ "$ADDED" -gt 0 ]; then
    echo "Stealth mode enabled: $ADDED paths added to .git/info/exclude"
  else
    echo "Stealth mode already configured ($ALREADY paths present)"
  fi
  # Check for tracked file warnings
  TRACKED=$(echo "$RESULT" | jq -r '.tracked_warning // [] | join(", ")')
  if [ -n "$TRACKED" ]; then
    echo "WARNING: These paths are tracked by git and must be removed from history separately: $TRACKED"
  fi
else
  echo "ERROR: Enable failed"
  echo "$RESULT"
fi

Subcommand: archive

Read configuration from .specify/extensions/spex-detach/spex-detach-config.yml and archive spec artifacts to the sibling specs repo.

RESULT=$("$DETACH_SCRIPT" archive)
EXIT_CODE=$?

if [ "$EXIT_CODE" -eq 0 ]; then
  SKIPPED=$(echo "$RESULT" | jq -r '.skipped // false')
  if [ "$SKIPPED" = "true" ]; then
    REASON=$(echo "$RESULT" | jq -r '.reason')
    echo "Archive skipped: $REASON"
  else
    DEST=$(echo "$RESULT" | jq -r '.archive_path')
    FILES=$(echo "$RESULT" | jq -r '.files_copied')
    COMMITTED=$(echo "$RESULT" | jq -r '.committed')
    echo "Archived $FILES files to: $DEST"
    [ "$COMMITTED" = "true" ] && echo "Auto-committed to project-specs repo."
  fi
else
  echo "ERROR: Archive failed"
  echo "$RESULT"
fi

Read the full file on GitHub · 77 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. 11d ago First seen · 77 lines · 16 tokens per session scan A a4852be7d96e

Subscribe to this mod's changes

speckit.spex-detach.detach is a command published in the GitHub repository rhuss/cc-spex (117 stars, last pushed 22d ago), licensed Apache-2.0. It adds 16 tokens to every session and 668 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 2026-08-30.