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/installable-toolsnpx skills add Generous-Corp/pulp --skill installable-toolsgit 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/installable-tools)<a href="https://agentmods.dev/skills/generous-corp/pulp/installable-tools"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/installable-tools.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 | $0.00107 | $0.01780 |
| Opus 5 | $0.00053 | $0.00890 |
| Sonnet 5 | $0.00021 | $0.00356 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade C, and why
installable-tools scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$H" How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
installable-tools — validate before you promote
A thing Pulp can install is not "done" when the code compiles or when it works in your repo checkout. It is done when a user who installed Pulp can install it, use it, and uninstall it — from their own project directory, not the Pulp source tree. Ship the README only after that is proven.
Why this skill exists
pulp tool install trace-processor shipped as a first-class tool (with a whole
showcase README promoting it) but worked only inside a Pulp git checkout:
the registry is resolved by walking up from cwd for
tools/packages/tool-registry.json, which installed users don't have, so it
errored Tool registry not found. It got that far because every validation ran
from inside the repo. Uninstall had a second latent problem — it never validated
the tool id, so uninstall ../../x could delete outside the managed tree.
Both are the kind of gap that only a from-the-user's-seat, full-lifecycle test catches. This skill is that checklist.
The bar (all four, every time)
- Install from OUTSIDE any checkout.
cdto a scratch dir whose parents contain notools/packages/tool-registry.json, pointPULP_HOMEat a throwaway dir, and run the install with the user-facingpulp(the installed binary or a fresh./build/pulp), not a raw in-repo build invocation. - Use it. Confirm the installed artifact actually runs / is found by the
command that consumes it (
pulp trace query, etc.). - Uninstall from OUTSIDE any checkout. It must remove exactly what it installed, name the path it deleted, and leave a clear message when nothing matched.
- Prove uninstall is safe. A hostile id (
..,../x,a/b, absolute path, empty) must be refused before any deletion, with a plant-a-victim test asserting nothing outside the managed tree was touched.
Only after 1–4 pass do you write or update the README/docs that tell users to run the command.
Registry resolution (why standalone works)
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 · 135 lines · 107 tokens per session scan C f18685e158f4
installable-tools is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,780 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
nemoclaw-contributor-implement-issue
Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
shopify-functions
Shopify Functions allow developers to customize the backend logic that powers parts of Shopify. Available APIs: Discount, Cart and Checkout Validation, Cart Transform, Pickup Point Delivery Option Generator, Delivery Customization, Fulfillment Constraints, Local Pickup Delivery Option Generator, Order Routing Location…
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.