source-command-unlatch

A switch for turning off latch’s project-judgment layer for the current installation. It can also turn that layer back on later.

In plain words
What is it for?
Use it to unlatch or re-latch the current installation, test behavior without latch, and restore managed AGENTS.md or CLAUDE.md sections.
Why use it?
It lets you compare the coding agent’s normal behavior with latch’s guidance, or temporarily work without that guidance. It records that latch is off and hides latch-managed instruction sections until you re-enable it.

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/open-latch/latch/source-command-unlatch
Any agent
npx skills add open-latch/latch --skill source-command-unlatch
Clone the repo
git clone --depth 1 https://github.com/open-latch/latch

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 994 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 $0.00046 $0.00994
Opus 5 $0.00023 $0.00497
Sonnet 5 $0.00009 $0.00199
Haiku 4.5 $0.00005 $0.00099

Measured 2d ago against content hash 03a160117652, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-command-unlatch 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.

.agents/skills/source-command-unlatch/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-command-unlatch

Use this skill when the user wants to turn latch's project-judgment layer off, compare against vanilla agent behavior, or re-latch after using the escape hatch.

Unlatched mode is in-place and install-level. It is not a controlled benchmark harness, uninstall, cloud flow, telemetry flow, or disposable project clone. It uses latch's existing full-disable sentinel plus an UNLATCHED receipt so future hooks show that latch influence is off for this latch install until the user re-latches. If the user changes repos before re-latching, latch remains off and should say so loudly. It also masks latch's managed CLAUDE.md / AGENTS.md regions in the current project/ancestor files while unlatched, then restores them when the user re-latches.

Command Template

First locate the latch checkout:

latch_home="${LATCH_HOME:-}"
if [ -z "$latch_home" ] && [ -n "${CLAUDE_KB_HOME:-}" ]; then
  latch_home="$CLAUDE_KB_HOME"
fi
if [ -z "$latch_home" ]; then
  search_dir="$PWD"
  while [ "$search_dir" != "/" ]; do
    for instruction_file in "$search_dir/AGENTS.md" "$search_dir/CLAUDE.md"; do
      if [ -f "$instruction_file" ]; then
        latch_home="$(sed -n 's|^UNLATCHED_LATCH_HOME=\(.*\)$|\1|p' "$instruction_file" | head -n 1)"
        [ -n "$latch_home" ] && break
        latch_home="$(sed -n 's|.*Follow `\([^`]*\)/README\.md` per-user setup.*|\1|p' "$instruction_file" | head -n 1)"
        [ -n "$latch_home" ] && break
      fi
    done
    [ -n "$latch_home" ] && break
    search_dir="$(dirname "$search_dir")"
  done
fi
if [ -z "$latch_home" ]; then
  candidate="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
  if [ -f "$candidate/src/mcp_server.py" ] && [ -d "$candidate/commands" ]; then
    latch_home="$candidate"
  fi
fi
if [ -z "$latch_home" ] || [ ! -f "$latch_home/src/mcp_server.py" ]; then
  echo "Could not find latch checkout; set LATCH_HOME to your latch install." >&2
  exit 1
fi

Then inspect state:

bash "$latch_home/bin/unlatch.sh"

Read the full file on GitHub · 108 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 108 lines · 46 tokens per session scan A 03a160117652

Subscribe to this mod's changes

source-command-unlatch is a skill published in the GitHub repository open-latch/latch (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 46 tokens to every session and 994 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

weave

Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 59 tokens

agentbro-release

Use when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask publication, or fixing a bad release.

shirenchuang/agentbro · 46 tokens

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

griddynamics/rosetta · 32 tokens

mcp-media-inbox-triage

Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.

zapier/gtm-cheat-codes · 43 tokens

customer-deck-builder

Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.

zapier/gtm-cheat-codes · 29 tokens

premortem

First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.

entropyvortex/meta-llm-charter · 59 tokens