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/forge-app-deliverynpx skills add Generous-Corp/pulp --skill forge-app-deliverygit 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/forge-app-delivery)<a href="https://agentmods.dev/skills/generous-corp/pulp/forge-app-delivery"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/forge-app-delivery.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 | $0.00084 | $0.06977 |
| Opus 5 | $0.00042 | $0.03488 |
| Sonnet 5 | $0.00017 | $0.01395 |
| Haiku 4.5 | $0.00008 | $0.00698 |
Grade A, and why
forge-app-delivery 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivering a Forge app
A Forge app is not one binary. It is a shell compiled in a different repository, a Python generator, a Rack plug-in, three plug-in formats, an uninstaller and a toolchain the user's machine fetches for itself. Every delivery failure recorded here came from one of those parts being absent, stale, or present but unreachable while every check reported success.
Read this before packaging anything, and before concluding that a feature "works".
The rule that would have saved the most time
Verify identity, not size, and never a signature. In a single day this project shipped:
- a 292-byte package that signed, notarized, stapled and passed Gatekeeper
while containing nothing (staged with symlinks instead of
dittocopies) - three plug-in bundles of 72 KB that installed cleanly and contained no
code (CMake creates
Contents/MacOSat configure time, so-eis true for an empty husk) - a 76 MB, four-payload, correctly-sized, notarized installer containing the wrong application entirely
The third is the important one. Size caught the first two and was useless for the third, because the payloads were the right size. Only identity distinguishes a correct build from a plausible one. Pick a string that exists in the current build and cannot exist in a stale or wrong one, and assert it in the packaging script:
hits=$(strings "$binary" 2>/dev/null | grep -cF "$SHELL_MARKER" || true)
Then expand the finished package and check the payload, rather than trusting the script that made it:
pkgutil --expand "Foo.pkg" out # --payload-files does NOT recurse into
# nested component payloads
The seam: the shell is built in the other repo
Forge app shells live in forge-seam/, are copied into a throwaway Forge
worktree by forge-seam/populate.sh (/tmp/forge-cur), compiled there, and
copied back by forge-seam/sync.sh.
Consequences that have each cost a cycle:
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 · 517 lines · 84 tokens per session scan A 5bbbf6217fca
forge-app-delivery is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 6,977 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…