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/osmantic/ods/pr-checkgit clone --depth 1 https://github.com/Osmantic/ODSWhat 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 | $0.00009 | $0.01571 |
| Opus 5 | $0.00005 | $0.00785 |
| Sonnet 5 | $0.00002 | $0.00314 |
| Haiku 4.5 | $0.00001 | $0.00157 |
Grade A, and why
pr-check 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Check Skill
Run all local CI checks before creating a PR. On failure, offer to fix issues interactively.
Philosophy: Ask Early, Ask Often
This skill should liberally use AskUserQuestion at decision points. CI check failures require judgment about whether to auto-fix, skip, or investigate. The user should approve each fix strategy.
- When a check fails — ask how to handle before auto-fixing
- When multiple checks fail — let the user prioritize which to fix first
- After all checks pass — ask about next steps (PR, review, etc.)
Pre-flight
Before running checks, verify the Makefile exists:
ls -la ods/Makefile
If the Makefile doesn't exist, inform the user and stop.
Checks Overview
Display to user before running:
Running 8 ODS checks:
- Shell lint -
bash -nsyntax check on all.shfiles- Python compile -
py_compilecheck on dashboard-api modules- Tier map + contract tests - Unit and contract test suite
- BATS unit tests - Shell library tests via BATS
- Smoke tests - Platform-specific smoke tests
- Installer simulation - Installer simulation harness
- Dashboard build/lint - ESLint + Vite production build
- Secret scan - Pre-commit hooks (gitleaks, private keys)
Execute Script
Run the full gate (covers checks 1-6):
cd ods && make gate
Then run dashboard checks:
cd ods/extensions/services/dashboard && npm run lint && npm run build
Then run secret scan:
pre-commit run --all-files
IMPORTANT: Stream output to user in real-time.
On Success
If all checks pass:
AskUserQuestion:
question: "All 8 PR checks passed! What would you like to do next?"
header: "Next"
multiSelect: false
options:
- label: "Create PR"
description: "Run /pr to create a pull request with these changes"
- label: "Run code review"
description: "Run /code-review before creating the PR"
- label: "Done"
description: "Checks passed — I'll handle the rest manually"
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 · 195 lines · 9 tokens per session scan A 4130d9eb6e70
pr-check is a command published in the GitHub repository Osmantic/ODS (5,819 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 1,571 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
resume-workflow
Resume workflow execution from current branch context.
start-development
Start development workflow process in Moira.
finish-feature
Start feature completion workflow in Moira.
PRODUCER
You are the production manager for this open-source VFX tool. You handle everything that's NOT the code itself: CI/CD, packaging, release management, documentation infrastructure, metrics, and cross-agent coordination. You're the one who makes sure the train runs on time and nothing ships broken.
ci-status
Real-time GitHub Actions workflow status and recent runs.
text-to-3d
Generate a static textured GLB from one subject description, locally.