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/seqgit 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/seq)<a href="https://agentmods.dev/commands/generous-corp/pulp/seq"><img src="https://agentmods.dev/badge/commands/generous-corp/pulp/seq.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 | $0.00023 | $0.00502 |
| Opus 5 | $0.00012 | $0.00251 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
seq 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
Work with a Pulp timeline project through the typed pulp seq surface. Read
.agents/skills/timeline/SKILL.md before changing a project; canonical project
JSON is immutable document state and must not be edited by hand.
Choose the operation from the user's request:
pulp seq schema
pulp seq validate <project.json>
pulp seq explain <project.json> [--sample-rate <hz>]
pulp seq apply <project.json> <commands.json> [--out <project.json>]
pulp seq export <project.json> --format <smf|dawproject> --plan
pulp seq export <project.json> --format smf --out <new-directory> \
pulp seq export <project.json> --format dawproject --out <new-file.dawproject> \
[--accept-loss <concept-id>]...
pulp seq import <file.mid|file.dawproject> --format <smf|dawproject> \
--out <new-directory>
If $ARGUMENTS names an operation or paths, use it to form the invocation. If
the requested mutation is not already represented by a typed command envelope,
inspect pulp seq schema and prepare the command JSON before applying it.
For export, always run --plan first and show the reported loss manifest to the
user. Continue only with the exact repeated --accept-loss <concept-id> values
the user accepts. There is no wildcard, force, or accept-all path, and accepting
a loss never removes it from the successful result's manifest.
Treat refusal as useful output: report required_consent exactly so it can be
reviewed and supplied on a later call. Do not invent concept IDs. Import and
export destinations must be new paths; do not delete or replace an existing
destination to make the command succeed. DAWproject import consumes and export
produces a standard .dawproject ZIP with a bounded root project.xml; the
canonical imported project is published into the new output directory.
After apply or import, validate the emitted project. Use explain when the
user needs the lowered playback plan, and render separately only when an audio
artifact is actually required.
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 · 44 lines · 23 tokens per session scan A 4b13573e1e60
seq is a command published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 502 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.