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.
npx agentmods add commands/gastownhall/gastown/backupgit clone --depth 1 https://github.com/gastownhall/gastownWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.00978 |
| Opus 5 | $0.00009 | $0.00489 |
| Sonnet 5 | $0.00003 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
backup 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dolt Backup
Sync production Dolt databases to filesystem backups with smart change detection.
Runs the same cycle as mol-dog-backup / the dolt-backup plugin.
Arguments: $ARGUMENTS
If --skip-offsite is passed, skip the iCloud rsync step.
Configuration
DOLT_DATA_DIR=~/gt/.dolt-data
BACKUP_DIR=~/gt/.dolt-backup
ICLOUD_DIR=~/Library/Mobile Documents/com~apple~CloudDocs/gt-dolt-backup
PROD_DBS: auto-discovered (databases with <name>-backup remotes)
BACKUP_TIMEOUT=120s per database
HANG_THRESHOLD=30s for server ping
DOLT_PORT=3307
Execution Steps
Step 1: Verify Dolt server is responsive
gt dolt status
Also ping directly to detect hangs:
timeout 30 dolt sql --host 127.0.0.1 --port 3307 --user root --password "" \
--no-tls -q "SELECT 1" --result-format csv
If the ping hangs (takes > 30s) or fails:
gt escalate "dolt-backup: Dolt server hung or unreachable" -s CRITICAL
STOP — do not attempt backups against a hung server.
Step 2: Discover databases with backup remotes
List directories in ~/gt/.dolt-data/ and check each for a <name>-backup remote:
ls ~/gt/.dolt-data/
For each directory (skip dotfiles):
cd ~/gt/.dolt-data/<name> && dolt backup
If the output contains <name>-backup, include it in the backup list.
Expected databases: hq, beads, gastown.
Step 3: Check each DB for changes and sync
For each database with a backup remote:
3a. Get current HEAD hash:
cd ~/gt/.dolt-data/<name> && dolt log -n 1 --oneline | head -1 | cut -d' ' -f1
3b. Compare against last backed-up hash:
cat ~/gt/.dolt-backup/<name>/.last-backup-hash 2>/dev/null
If hashes match and current hash is not "unknown", skip (unchanged).
3c. Sync if changed:
cd ~/gt/.dolt-data/<name> && timeout 120 dolt backup sync <name>-backup
3d. Record successful hash:
mkdir -p ~/gt/.dolt-backup/<name>
echo "<current_hash>" > ~/gt/.dolt-backup/<name>/.last-backup-hash
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.
- yesterday First seen · 132 lines · 17 tokens per session scan A 3c146bfba720
backup is a command published in the GitHub repository gastownhall/gastown (17,849 stars, last pushed 13d ago), licensed MIT. It adds 17 tokens to every session and 978 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.