terminator:install
Install the terminator kill hooks into the current project. Installs single-kill.sh and/or double-kill.sh as Stop hooks, each bound to a non-obvious phrase, merging into .claude/settings.local.json without clobbering existing hooks. Use when the user asks to "install terminator", "set up the kill hooks", "add single kill", "add double kill", or "enable session termination".
What this skill does
# Terminator: Install
Install one or both kill hooks into the **current project**. There are two independent scripts;
which behaviour you get is determined by **which script is installed**, not by a flag:
- `single-kill.sh` — phrase fires → terminate Claude. Terminal stays open.
- `double-kill.sh` — phrase fires → terminate Claude **and** the terminal shell that launched it.
Matching is **contains** (the message need only contain the phrase; robust to model preambles),
case-sensitivity configurable. The only hard safety rule in the kill path is: never signal pid ≤ 2.
> Scope: install into the project's `.claude/`. Do not touch global `~/.claude/settings.json`
> unless the user explicitly asks.
## Step 1 — Which hooks?
Ask the user (or read from `$ARGUMENTS`): **single**, **double**, or **both**.
## Step 2 — Phrases + case sensitivity
- Single-kill phrase (suggest a generated phrase such as `term-single-<16 random lowercase hex chars>`).
- Double-kill phrase (suggest a generated phrase such as `term-double-<16 random lowercase hex chars>`).
- Run the phrase strength gate below before accepting each phrase.
- Use distinct phrases; if both hooks are installed, neither phrase may equal or contain the other.
- Case-sensitive (default) or case-insensitive (`AskUserQuestion`).
### Phrase Strength Gate
Terminator uses a contains-match against the final assistant message, so obvious phrases are unsafe:
normal conversation or quoted user text could trigger the hook. Do not write `.claude/terminator.json`
until every configured phrase passes this gate.
A phrase is acceptable only if all of these are true:
- It is at least 18 characters after trimming whitespace.
- It includes an uncommon random component, such as 16+ lowercase hex characters, 12+ base64url
characters, or four unrelated random words.
- It is not a normal completion word or short instruction, including `done`, `finish`, `finished`,
`complete`, `completed`, `exit`, `quit`, `stop`, `kill`, `terminate`, `single kill`,
`double kill`, `all done`, `goodbye`, or close variants.
- It is not a phrase the assistant is likely to say in a normal final answer.
- If `case_sensitive` is false, the lowercased phrase still passes the same gate.
- If both hooks are installed, the two phrases are distinct and neither phrase contains the other.
If a requested phrase fails, do not install with it. Explain the failing condition briefly and ask
for a stronger phrase or offer a generated one.
## Step 3 — Confirm (destructive)
```
About to install in this project:
single-kill.sh phrase="<single phrase>" -> ends Claude
double-kill.sh phrase="<double phrase>" -> ends Claude + terminal
case sensitive : <true|false>
```
## Step 4 — Copy the chosen script(s)
```bash
mkdir -p .claude/hooks
# copy ${CLAUDE_PLUGIN_ROOT}/templates/single-kill.sh -> .claude/hooks/single-kill.sh (if single/both)
# copy ${CLAUDE_PLUGIN_ROOT}/templates/double-kill.sh -> .claude/hooks/double-kill.sh (if double/both)
chmod +x .claude/hooks/*-kill.sh
```
## Step 5 — Write config
```bash
jq -n --arg s "<single phrase>" --arg d "<double phrase>" --argjson cs <true|false> \
'{single_killphrase:$s, double_killphrase:$d, case_sensitive:$cs}' > .claude/terminator.json
```
(Omit the key for a script you are not installing; each script only reads its own key.)
## Step 6 — Merge the Stop hook(s) — never clobber existing hooks
For each script being installed, merge its entry in idempotently:
```bash
[ -f .claude/settings.local.json ] || echo '{}' > .claude/settings.local.json
for s in single-kill.sh double-kill.sh; do # restrict to the ones you installed
cmd="\"\$CLAUDE_PROJECT_DIR\"/.claude/hooks/$s"
tmp="$(mktemp)"
jq --arg cmd "$cmd" --arg s "$s" '
.hooks.Stop = ((.hooks.Stop // [])
| if any(.hooks[]?.command? // "" | contains($s)) then .
else . + [{matcher:"", hooks:[{type:"command", command:$cmd, timeout:10000}]}]
end)
' .claude/settings.local.json > "$tmp" && mv "$tmp" .claude/settings.local.json
done
```
## Step 7 — Verify & report
```bash
ls -la .claude/hooks/*-kill.sh
cat .claude/terminator.json
jq '.hooks.Stop' .claude/settings.local.json
```
```
## Terminator installed
single-kill.sh : phrase "<s>" (Claude only) [if installed]
double-kill.sh : phrase "<d>" (Claude + terminal) [if installed]
case sensitive : <true|false>
Other Stop hooks: preserved
Takes effect after a session restart (/exit and start a new Claude session).
Change phrases: /terminator:update Uninstall: /terminator:remove
```
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.