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 skills/generous-corp/pulp/contributenpx skills add Generous-Corp/pulp --skill contributegit 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/skills/generous-corp/pulp/contribute)<a href="https://agentmods.dev/skills/generous-corp/pulp/contribute"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/contribute.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 | $0.00073 | $0.02978 |
| Opus 5 | $0.00036 | $0.01489 |
| Sonnet 5 | $0.00015 | $0.00596 |
| Haiku 4.5 | $0.00007 | $0.00298 |
Grade A, and why
contribute 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to Pulp / Forge without the maintainer setup
You do not need Shipyard, Tart, VMs, self-hosted runners, or write access. Those are maintainer infrastructure. Your job is a clean, tested, well-scoped change plus an honest account of what you could not verify. A maintainer takes it from there.
Works the same under Claude Code and Codex — this file is the shared source of
truth (.agents/skills/), not a per-tool doc.
The one rule that saves the most rework
Say what you did not do. A contribution that fixes one thing and clearly lists three unverified things is far more useful than one that implies everything was checked. The maintainer's expensive step is discovering an unstated gap after merge. Write the gaps down and you are done; hide them and you cost a debugging session.
1. Where does the change belong?
| Change | Repo |
|---|---|
DSP, core/**, format adapters, runtime, view/state layers |
Pulp (Core SDK) |
| Anything any Pulp plugin would want | Pulp |
| Generating plugins — Forge's UI, templates, catalog, workflow | Forge |
Fixing a bug you hit while building with Forge, but the bug is in core/** |
Pulp |
That last row is the common case and the easy one to get wrong. If you found it from the plugin side but the defect lives in the shared layer, it belongs in Pulp, and it should be split out from your product work.
Split by concern, not by session. If one branch contains two unrelated core fixes plus a feature, prepare them as separate patches in dependency order and say which are independent. Independent bug fixes land fast; anything that changes how something sounds gets scrutinized, and shouldn't hold them up.
2. Never touch version files
Do not edit CMakeLists.txt VERSION, .claude-plugin/plugin.json,
marketplace.json, or CHANGELOG.md.
Pulp assigns versions after merge (version-at-land) from the diff. A
contributor-side bump only creates a conflict that makes the PR obsolete — it
does not help. Same for changelog entries: they are regenerated.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 260 lines · 73 tokens per session scan A 788215745bc4
contribute is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 2,978 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…