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.
git 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/gpu)<a href="https://agentmods.dev/commands/generous-corp/pulp/gpu"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/gpu/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/generous-corp/pulp/gpu"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/gpu.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.00355 |
| Opus 5.5 | $0.00008 | $0.00142 |
| Sonnet 5.5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
gpu 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 1mo 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
Start with the cheapest truthful path:
pulp doctor gpu --json
pulp gpu recipes list --json
pulp gpu recipes list --symptom <exact-symptom-token> --json
pulp gpu recipes show <recipe-id> --json
Then run the selected closed recipe into a new path-confined artifact directory:
pulp gpu probe --recipe <recipe-id> --artifacts /tmp/pulp-gpu-evidence --json
Exit 0 is a measured pass, exit 1 is a completed measured failure, and exit 2
is unavailable or unverified. Runtime, internal-validation, and artifact
publication failures also use typed unverified JSON and exit 2; never read
them as completed measurements. Preserve the typed JSON, gpu_evidence_id,
adapter status/class, numeric oracle, and artifact digests. An unknown or
unverified adapter is not an authentic hardware claim, even when the backend is
Dawn/WebGPU. Never infer correctness from a screenshot alone.
Use --negative-control only to prove that the declared mutation fails for its
intended causal reason. Do not run GPU readback, validation, or artifact writing
on an audio thread. For a correlated trace, capture through the canonical
exact-instance trace lifecycle and use /trace with gpu-probe over the same
flushed .pftrace.
The recipe catalog is Pulp's product/tool workflow. It does not authorize a generic rendering API or a DPR policy; those remain evidence-gated Vellum follow-up work.
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.
- 1mo ago First seen · 38 lines · 20 tokens per session scan A 20b01465844c
gpu is a command published in the GitHub repository Generous-Corp/pulp (22 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 355 once invoked, about $0.0001 per session on Opus 5.5. 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
ee-review
Produce an EE decision document (escalating intervention ladder + binding constraints, cited and confidence-graded) for an analog/placement-blocked board.
cortex-m
Generate Cortex-M startup code or a linker script, configure a core subsystem, decode a fault, or add DWT timing.
debug-embedded
Attach a debugger, halt and inspect a target, decode fault registers, or configure ITM, SWO, or ETM trace.
debug
A command-line debugging toolkit for embedded programs using J-Link or OpenOCD, tools that connect a computer to a microcontroller for inspection.
la
A command for capturing and decoding signals with a Saleae logic analyzer, a device that records electrical digital signals over time. It supports buses such as UART, SPI, and I2C, which are common ways chips communicate with peripherals.
map
A parser for Keil compiler map files, which are build reports describing where program code and data are placed in memory. It reports object sizes, memory regions, symbols, and stack or heap details.