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 chiruu12/OSS-Skills --skill oss-explore-repogit clone --depth 1 https://github.com/chiruu12/OSS-SkillsWrote 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/chiruu12/oss-skills/oss-explore-repo)<a href="https://agentmods.dev/skills/chiruu12/oss-skills/oss-explore-repo"><img src="https://agentmods.dev/badge/skills/chiruu12/oss-skills/oss-explore-repo/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/chiruu12/oss-skills/oss-explore-repo"><img src="https://agentmods.dev/badge/skills/chiruu12/oss-skills/oss-explore-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.02673 |
| Opus 5.5 | $0.00032 | $0.01069 |
| Sonnet 5.5 | $0.00016 | $0.00535 |
| Haiku 4.5 | $0.00008 | $0.00267 |
Grade A, and why
oss-explore-repo 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 1mo 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Repo
Explore a codebase the way experienced contributors do. by understanding the architecture, the patterns, and the domain language before touching anything.
Purpose
Different from oss-prep-to-contribute (which is issue-specific and focused on one code path). This skill is for building broad understanding of a repo. Useful when a contributor wants to become a regular contributor rather than make a single drive-by PR. Also useful for GSoC candidates who need to demonstrate deep project understanding in their proposals.
Prerequisites
- A repo cloned locally
ghCLI authenticated- A reason to explore (casual learning, planning to contribute, GSoC proposal, evaluating the project)
Process
1. Understand the contributor's goal
Before exploring anything, ask:
- "Why are you exploring this repo? (Casual learning / planning to contribute regularly / GSoC proposal / evaluating whether to use it)"
- "How much time do you want to spend? (Quick overview / deep dive)"
This shapes the depth. A GSoC candidate needs deep understanding. Someone evaluating a library needs a quick architecture scan.
2. Map the project from the outside in
Start with what the project DOES, not what the code looks like. Read:
# Project identity
cat README.md
cat docs/index.md 2>/dev/null || cat docs/README.md 2>/dev/null
# What problem does it solve?
gh api repos/{owner}/{repo} --jq '{description, homepage, topics, language, stargazers_count, open_issues_count}'
The user should be able to explain what the project does to a non-technical person before reading a single source file.
Thinking gate:
"Explain what this project does in one sentence. Who uses it? What problem does it solve? Don't use the README's words. rephrase it as if you're explaining to a friend who doesn't code."
If the user can't do this clearly, they need to read more docs before touching code.
3. Understand the architecture
Use Explore agents to map:
# Directory layout
ls -la
ls src/ lib/ app/ 2>/dev/null
ls -la */
# Entry points
cat package.json 2>/dev/null | jq '.main, .bin, .scripts'
cat setup.py 2>/dev/null || cat pyproject.toml 2>/dev/null
cat Makefile 2>/dev/null | head -30
cat Cargo.toml 2>/dev/null | head -30
# Key abstractions
grep -rn "class \|interface \|trait \|type \|struct " src/ lib/ \
--include="*.ts" --include="*.py" --include="*.go" --include="*.rs" --include="*.java" | head -40
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.
- 1mo ago First seen · 250 lines · 81 tokens per session scan A ea8d2da4aa43
oss-explore-repo is a skill published in the GitHub repository chiruu12/OSS-Skills (61 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 2,673 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
chief-data-officer-advisor
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data…
wrap-up
Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own now", "give me the summary", "recap the agent", or when the orchestrator routes…
ctf-malware
Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…
deploy-site
Deploys an existing Power Pages site to a Power Pages environment using PAC CLI. Routes SPA sites to the existing build and upload-code-site workflow, and PAC-downloaded non-SPA (classic) sites to an isolated upload workflow with explicit data-model and website-identity checks. Handles tooling verification…
create-formal-verification-skill
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers…
principle-type-system-discipline
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.