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/audio-inspectgit 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/audio-inspect)<a href="https://agentmods.dev/commands/generous-corp/pulp/audio-inspect"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/audio-inspect.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 | $0.00033 | $0.01317 |
| Opus 5 | $0.00016 | $0.00659 |
| Sonnet 5 | $0.00007 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
audio-inspect 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Audio Inspector is a separate developer tool window that shows what audio is
flowing right now, built on the realtime audio probe. It is a sibling of the
layout inspector (Cmd+I / Ctrl+I), not a tab inside it — the two tools own
independent state models but share the same command-routing and window
primitives.
Opening it
The window opens/focuses through a rebindable command registered with the
shell's CommandRegistry:
- Default chord:
Cmd+Shift+A(macOS) /Ctrl+Shift+A(Windows/Linux). - Command id:
AudioInspectorWindow::kToggleAudioInspector(ASCIIPLAI), distinct from the layout inspector'sPLPI. - Rebind it like any other command via the
KeyMappingEditor; the binding persists throughShortcutMap. - Env var: launch with
PULP_AUDIO_INSPECTOR=1to open the window at startup. - CLI:
pulp run --audio-inspector(forwards the flag + sets the env var). Composes with--screenshotto also capture the panel as<stem>.audio-inspector.pngin a headless run.
Programmatic readout (agents / CI)
When you can't look at a window, read the probe as JSON:
pulp run --audio-probe-json /tmp/probe.json # headless one-shot dump + exit
MCP clients can call the existing pulp-mcp server tool
pulp_audio_probe_json for the same one-shot readout. That tool wraps
pulp run --audio-probe-json, accepts optional target and frames
arguments, and returns the probe object as structuredContent.
--audio-probe-json is UI-headless, not guaranteed silent: it launches the live
standalone host and may activate the system audio output. Announce before using
it locally, cap the run, and use /audio-harness / Audio Doctor for no-speaker
offline checks.
Use this as the first live-health check for audio-dev work. A useful result has
advancing callbacks; non-zero peak_max / rms_max when audio is expected;
and zero clip/NaN counters. callbacks > 0 with zero levels means the observed
output boundary is silent, not that the probe is broken. Escalate to offline
Audio Doctor or a scenario render when the live probe is healthy but the sound
is still wrong, because this snapshot cannot prove response, THD, phase,
latency, or tuning.
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 · 115 lines · 33 tokens per session scan A 0767536b1485
audio-inspect is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,317 once invoked, about $0.0002 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.