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/lap-platform/lap/releasegit clone --depth 1 https://github.com/Lap-Platform/LAPWhat 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 | $0.00000 | $0.00578 |
| Opus 5 | $0.00000 | $0.00289 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
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 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release a new version of LAP
Bump the version and publish to PyPI + npm.
Arguments
- $ARGUMENTS: The new version number (e.g. "0.5.0"). If empty, ask the user.
Steps
-
Validate version: Ensure the version argument is a valid semver string (X.Y.Z). If not provided or invalid, ask the user for the version number.
-
Run tests first: Run
PYTHONUTF8=1 python -m pytest tests/ -q --timeout=30from the project root. If any tests fail, STOP and report the failures. Do not proceed with a broken build. -
Bump version in all files:
lap/__init__.py-- update__version__pyproject.toml-- updateversionsdks/typescript/package.json-- updateversion
-
Update CHANGELOG.md: Add a new
## [X.Y.Z] - YYYY-MM-DDsection at the top (below the header). Ask the user for a summary of changes, or generate one from recent git log if the user says to auto-generate. -
Update README.md: Review the changelog for this release. If it includes new features, new commands, new IDE support, or changed behavior that users need to know about, update README.md accordingly (Quick Start, Use as an Agent Skill, Ecosystem table, badges, etc.). If the release is only bug fixes or internal changes, skip this step.
-
Commit: Stage all changed files and commit with message:
chore: bump to vX.Y.Z with changelog -
Push: Push to origin/main.
-
Create GitHub Release: Run
gh release create vX.Y.Z --title "vX.Y.Z" --notes-file CHANGELOG_SECTIONwhere CHANGELOG_SECTION contains only the new version's changelog section. -
Monitor publish workflows: After the release is created, poll the two workflow runs:
Publish to PyPIPublish to npm
Use
gh run list --limit 4to find the run IDs, then usegh run watch <run-id>to monitor each. Report the final status of each workflow to the user (success/failure). If a workflow fails, show the failure logs usinggh run view <run-id> --log-failed.
Important
- Never skip tests before releasing
- All three version files must be in sync
- The GitHub release triggers the publish workflows via
on: release: types: [published] - Do not publish manually -- always use the GitHub Actions workflows
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 · 42 lines · 0 tokens per session scan A ca3a040f8f0a
release is a command published in the GitHub repository Lap-Platform/LAP (346 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 578 tokens. 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
add_and_commit
add and commit with descriptive message.
smoke-test
npm run test:smoke.
checkpoint
Create a checkpoint by staging the changes you have made using git. usage: git [-v | --version] [-h | --help] [-C ] [-c = ] [--exec-path[= ]] [--html-path] [--man-path] [--info-path] [-p | --paginate | -P | --no-pager] [--no-replace-objects] [--bare] [--git-dir= ] [--work-tree= ] [--namespace= ] [--super-prefix= ]…
templates
Manage locally-stored email templates for composing messages with variable substitution.
symfony-api-errors
Design API Platform 4.3 error handling — RFC 7807.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.