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 skills add future-architect/uzomuzo-oss --skill scan-before-addgit clone --depth 1 https://github.com/future-architect/uzomuzo-ossWrote 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/future-architect/uzomuzo-oss/scan-before-add)<a href="https://agentmods.dev/skills/future-architect/uzomuzo-oss/scan-before-add"><img src="https://agentmods.dev/badge/skills/future-architect/uzomuzo-oss/scan-before-add/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/future-architect/uzomuzo-oss/scan-before-add"><img src="https://agentmods.dev/badge/skills/future-architect/uzomuzo-oss/scan-before-add.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00089 | $0.02655 |
| Opus 5.5 | $0.00036 | $0.01062 |
| Sonnet 5.5 | $0.00018 | $0.00531 |
| Haiku 4.5 | $0.00009 | $0.00265 |
Grade A, and why
scan-before-add 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 4d ago.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Before Add: $ARGUMENTS
Scan the candidates with uzomuzo before a dependency is added, and leave a record of what was checked and who decided.
When an AI agent (or a person) adds a library, the change usually shows which library was added but not what was checked before adding it. This skill runs uzomuzo scan on the candidates and writes that down: the verdict, the evidence uzomuzo printed, what could not be fetched, who proposed each candidate, who chose, and whether a person has reviewed the choice.
Contract: uzomuzo returns maintenance evidence. You choose and add a dependency only within the authority the person gave you. The record keeps uzomuzo's output and your own reading apart, and states whether a person has reviewed the choice. This skill never turns a verdict into an approval.
Prerequisites
uzomuzoonPATH(see Installation). Check withuzomuzo --version.- Network access: uzomuzo queries deps.dev, OSV, and GitHub.
GITHUB_TOKENis optional. Without it, archive detection relies on the Scorecard "Maintained" check only (no direct GitHub API check), and the last human commit date, the human/bot commit ratio, and fork detection are not available (details). The verdict for the same package can differ -- a repository archived on GitHub has come back ascautionwithout a token andreplacewith one. Record whether the token was set ("unknown" if you cannot check; do not infer it from rate-limit numbers); never print its value.
Step 1: Establish the purpose and the candidates
- Purpose -- one sentence on what the dependency is for, in the person's words.
- Requirements -- conditions the person already stated (license, ecosystem, "must be maintained", and so on). Write "none stated" if there are none.
- Authority -- write down three things separately; later steps depend on them: (a) did the person name the package or ask you to choose one, (b) did the person ask you to add it to the manifest, or only to recommend, and (c) did the person tell you not to ask questions.
- Candidates:
- If the person named a package, that package is the candidate. You may add alternatives you think are worth comparing.
- If you are choosing, pick the candidates that meet the purpose and scan all of them before you pick one, not only the one you end up adding. Consider whether the standard library already covers the purpose. If you scan only one candidate, write down why.
- PURLs:
- Use the name the package manager uses, not the import name:
pkg:pypi/[email protected], notpkg:pypi/yaml. - Keep Go major-version suffixes:
pkg:golang/github.com/Masterminds/semver/[email protected]. - Encode npm scopes:
pkg:npm/%40types/[email protected]. - If a package name is ambiguous, ask rather than guess (unless told not to ask; then state your interpretation in the record).
- Use the name the package manager uses, not the import name:
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.
- 4d ago First seen · 113 lines · 89 tokens per session scan A 9e2b039435a3
scan-before-add is a skill published in the GitHub repository future-architect/uzomuzo-oss (42 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 2,655 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
implementing-supply-chain-security-with-in-toto
Implement software supply chain integrity verification for container builds using the in-toto framework to create cryptographically signed attestations across CI/CD pipeline steps.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
go
Use when writing, reviewing, testing, or shipping Go code and HTTP services: idioms, %w error wrapping, goroutine/context/errgroup concurrency, net/http 1.22 routing, log/slog, project layout, table-driven tests, Go hardening. NOT language-agnostic threat modeling (that is secure-coding), NOT Dockerfile/CI shipping…
bubbletea-testing
Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…