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/contentgit 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/content)<a href="https://agentmods.dev/commands/generous-corp/pulp/content"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/content.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 | $0.00000 | $0.00621 |
| Opus 5 | $0.00000 | $0.00311 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
content 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.
What it actually says
/content
Validate, preview, install, update, list, rescan, remove, or reveal data-only Pulp content packs.
Use this for .pulpcontent archives or content-pack directories that contain presets, themes, samples, wavetables, or other user-facing data for an installed plugin.
Why it matters:
- plugin authors ship expansion packs without custom installers;
- users can validate, see reload/restart expectations, and remove packs without losing their own presets;
- plugins discover supported content through declared runtime capabilities.
Content packs are not dependency packages and are not project-transforming kits.
Common commands:
pulp content validate <path> --json
pulp content preview <path> --plugin-runtime <manifest> --json
pulp content install <path> --plugin <plugin-id> --yes
pulp content update <path> --plugin <plugin-id> --yes
pulp content list --plugin <plugin-id> --json
pulp content rescan --json
pulp content reveal <package-id> --plugin <plugin-id> --version <version>
pulp content remove <package-id> --plugin <plugin-id> --version <version> --yes
Workflow:
- Validate the pack.
- Preview against the trusted plugin runtime manifest when available.
- Explain target plugin, supported kinds, install path, and hot-reload/rescan/restart policy.
- Install or update only after explicit approval.
- Use
rescanto rebuild the local content index after manual changes or repair; index entries include the targetplugin_idand installed manifest digest for audit/drift checks. - Remove only the installed content-pack root.
Trust rules:
- content commands copy data only; they never run package CMake, JavaScript, scripts, dynamic libraries, or remote fetches;
.pulpcontentarchives must includefiles.sha256.json, and every payload file must be listed and hash-matched before preview/install/update;previewreads a trusted plugin runtime manifest and reports compatibility plus hot-reload/rescan/restart policy;- install/update/remove require explicit approval and safe single-component plugin/package/version ids;
- removal deletes only the installed content-pack root; user-created presets must survive.
Runtime plugins opt in through ContentRegistry or PresetManager, preferably from an embedded pulp.plugin-runtime.json. In-app installers and drop handlers should call preview_content_pack_install(...), show the target path and reload policy, then call install_content_pack(..., approved=true) only after approval.
Plugin authors should declare content support in CMake:
pulp_add_plugin(MySynth
...
CONTENT_CAPABILITIES content.presets.v1
CONTENT_KINDS presets
CONTENT_HOT_RELOAD_KINDS presets)
That generates and bundles pulp.plugin-runtime.json, so agents and validators can tell which packs match the plugin and whether users need hot reload, rescan, or restart before install.
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 · 58 lines · 0 tokens per session scan A b4f8e1aac5b0
content is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 621 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 2026-09-04.
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.