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/generous-corp/pulp/minosgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/generous-corp/pulp/minos)<a href="https://agentmods.dev/commands/generous-corp/pulp/minos"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/minos.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00024 | $0.00974 |
| Opus 5 | $0.00012 | $0.00487 |
| Sonnet 5 | $0.00005 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
minos 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 today.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minimum-OS tooling. The "minimum OS" a build needs is the highest minimum among everything linked into it — the SDK's own libraries (Skia, Dawn, the JS engine), the C++ runtime, and the plugin's own compiled code. These commands read that floor straight from the built artifact, so it's the honest number, not a guess from a manifest.
Full explainer: docs/guides/minimum-os-support.md.
Measure one binary
Report the minimum OS a single built binary needs:
pulp minos measure <path-to-binary>
<path-to-binary> can be a .dylib / .so / .dll, a .a static archive, an executable, or a plugin bundle's inner binary (e.g. MyPlugin.vst3/Contents/MacOS/MyPlugin). Output is <kind> <floor>, e.g. macho 13.3 (macOS 13.3), elf 2.34 (glibc 2.34), pe 10.0 (Windows 10).
If $ARGUMENTS names a binary, measure it:
pulp minos measure $ARGUMENTS
Sweep every downstream consumer
Rebuild every downstream demo/example against one installed Pulp SDK and report each project's floor next to the SDK's floor — a DRIFT flag means a consumer's binaries ended up needing a higher OS than the SDK declares (usually a build host leaking a newer toolchain). Non-zero exit on any build failure or drift, so it can gate a release.
Dry-run first to see the plan (no clones, no builds):
pulp minos sweep --sdk-prefix /path/to/installed-sdk --dry-run
Then run it (optionally scope with --only, capture with --json):
pulp minos sweep --sdk-prefix /path/to/installed-sdk
pulp minos sweep --sdk-prefix /path/to/installed-sdk --only pulp-example-plugins,pulp-gpu-nam
pulp minos sweep --sdk-prefix /path/to/installed-sdk --json /tmp/sweep.json
The SDK prefix is an unpacked installed SDK (the directory containing lib/cmake/Pulp). Build a fresh one with cmake --install <build> --prefix <prefix>.
Notes:
- The registry of what to sweep is
planning/sdk-consumers/consumers.yaml(private submodule); per-repo build knobs are intools/scripts/sdk_consumer_sweep_recipes.yaml. README/PKG-only release mirrors are skipped automatically. pulp minos sweepneeds PyYAML:python3 -m pip install pyyaml.- The sweep clones and builds many repositories, so it's a CLI-only command (not exposed over MCP). The
pulp minos measureop is available over MCP aspulp_minos.
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.
- today First seen · 79 lines · 24 tokens per session scan A a0afeda29d84
minos is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 974 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 2026-09-04.
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.