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/mediar-ai/terminator/releasegit clone --depth 1 https://github.com/mediar-ai/terminatorWhat 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 | $0.00008 | $0.00389 |
| Opus 5 | $0.00004 | $0.00195 |
| Sonnet 5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
release 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.
What it actually says
Bump the version number across all packages using the terminator CLI and create a new release.
Usage:
/release- Automatically bump patch version and push (one-shot, no questions)/release patch- Bump patch version (e.g., 0.20.6 → 0.20.7)/release minor- Bump minor version (e.g., 0.20.6 → 0.21.0)/release major- Bump major version (e.g., 0.20.6 → 1.0.0)
Steps:
- Read current version from
terminator-cli/Cargo.toml - If no argument provided, default to patch bump
- Run
terminator release <patch|minor|major>to:- Bump version across all packages (Cargo.toml, package.json)
- Create git tag (v{version})
- Push commit and tag
- Read git commits since last version tag
- Update CHANGELOG.md with new version section and changes
- Commit changelog update: "chore: update CHANGELOG for v{version}"
- Push changelog commit
Important:
- NO user confirmation needed - just do it automatically
- Uses terminator CLI for version management (syncs all packages)
- Git tag triggers CI/CD workflows:
publish-npm.yml→ @mediar-ai/terminator to npmpublish-mcp.yml→ terminator-mcp-agent to npmci-wheels.yml→ Python wheels to PyPI
- Be fast and efficient - this is a one-shot command
- CHANGELOG.md follows Keep a Changelog format
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.
- 2d ago First seen · 34 lines · 8 tokens per session scan A ba59af54fd1f
release is a command published in the GitHub repository mediar-ai/terminator (1,627 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 389 once invoked, about $0.0000 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
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
generate-docs
Generate or update project documentation including README, API docs, and changelog.
estimate-azure-cost
Estimate Azure resource costs and provide optimization recommendations.
commit
Act as a senior software engineer to commit changes to the repository in non-interactive modes ONLY, using the following template.
validate-pipeline
Validate data pipeline configuration and data quality rules.
aidd-churn
Rank files by hotspot score to identify prime candidates for refactoring before PR review.