github

A local command-line tool for accessing selected GitHub API data, including repository activity, agent tasks, applications, billing, and security advisories.

In plain words
What is it for?
Use it to read supported GitHub data, search or sync cached records, and preview or—with explicit confirmation—execute supported changes such as creating an agent task.
Why use it?
It provides structured GitHub data for coding-agent tasks and previews write operations before they are carried out.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/justvugg/tools-factory/github
Any agent
npx skills add JustVugg/tools-factory --skill github
Clone the repo
git clone --depth 1 https://github.com/JustVugg/tools-factory

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,978 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01978
Opus 5 $0.00016 $0.00989
Sonnet 5 $0.00007 $0.00396
Haiku 4.5 $0.00003 $0.00198

Measured yesterday against content hash 05357677a887, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github 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 yesterday.

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.

library/tools/github/skills/github/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

github

Generated by Gutenberg. Use this skill to call the github API through the local github CLI.

When to use

  • The user asks for data exposed by github (actions, activity, agent-tasks, agents, apps, billing).
  • An agent task needs structured JSON from https://api.github.com.
  • You need to perform a write/destructive operation on github — always preview first, run with --yes only on explicit user confirmation.

How to invoke

The skill assumes the generated CLI is on PATH (or invoke via scripts/use-go.sh run ./cmd/github from the project directory).

github operations
github call meta/root --json
github sync --json
github search "<keyword>" --json

Preview a write operation (default behavior, no side effects):

github call agent-tasks/create-task-in-repo --data '{"example":true}' --json

Execute it (only after explicit user confirmation):

github call agent-tasks/create-task-in-repo --data '{"example":true}' --yes --json

Authentication

No authentication required.

Operations index

  • meta/root (GET /) — read — GitHub API Root
  • security-advisories/list-global-advisories (GET /advisories) — read — List global security advisories
  • security-advisories/get-global-advisory (GET /advisories/{ghsa_id}) — read — Get a global security advisory
  • agent-tasks/list-tasks-for-repo (GET /agents/repos/{owner}/{repo}/tasks) — read — List tasks for repository
  • agent-tasks/create-task-in-repo (POST /agents/repos/{owner}/{repo}/tasks) — write — Start a task
  • agent-tasks/get-task-by-repo-and-id (GET /agents/repos/{owner}/{repo}/tasks/{task_id}) — read — Get a task by repo
  • agent-tasks/list-tasks (GET /agents/tasks) — read — List tasks
  • agent-tasks/get-task-by-id (GET /agents/tasks/{task_id}) — read — Get a task by ID
  • apps/get-authenticated (GET /app) — read — Get the authenticated app
  • apps/create-from-manifest (POST /app-manifests/{code}/conversions) — write — Create a GitHub App from a manifest
  • apps/get-webhook-config-for-app (GET /app/hook/config) — read — Get a webhook configuration for an app
  • apps/update-webhook-config-for-app (PATCH /app/hook/config) — write — Update a webhook configuration for an app
  • apps/list-webhook-deliveries (GET /app/hook/deliveries) — read — List deliveries for an app webhook
  • apps/get-webhook-delivery (GET /app/hook/deliveries/{delivery_id}) — read — Get a delivery for an app webhook
  • apps/redeliver-webhook-delivery (POST /app/hook/deliveries/{delivery_id}/attempts) — write — Redeliver a delivery for an app webhook
  • apps/list-installation-requests-for-authenticated-app (GET /app/installation-requests) — read — List installation requests for the authenticated app
  • apps/list-installations (GET /app/installations) — read — List installations for the authenticated app
  • apps/get-installation (GET /app/installations/{installation_id}) — read — Get an installation for the authenticated app
  • apps/delete-installation (DELETE /app/installations/{installation_id}) — destructive — Delete an installation for the authenticated app
  • apps/create-installation-access-token (POST /app/installations/{installation_id}/access_tokens) — write — Create an installation access token for an app
  • apps/suspend-installation (PUT /app/installations/{installation_id}/suspended) — write — Suspend an app installation
  • apps/unsuspend-installation (DELETE /app/installations/{installation_id}/suspended) — destructive — Unsuspend an app installation
  • apps/delete-authorization (DELETE /applications/{client_id}/grant) — destructive — Delete an app authorization
  • apps/check-token (POST /applications/{client_id}/token) — write — Check a token
  • apps/reset-token (PATCH /applications/{client_id}/token) — write — Reset a token
  • apps/delete-token (DELETE /applications/{client_id}/token) — destructive — Delete an app token
  • apps/scope-token (POST /applications/{client_id}/token/scoped) — write — Create a scoped access token
  • apps/get-by-slug (GET /apps/{app_slug}) — read — Get an app
  • classroom/get-an-assignment (GET /assignments/{assignment_id}) — read — Get an assignment
  • classroom/list-accepted-assignments-for-an-assignment (GET /assignments/{assignment_id}/accepted_assignments) — read — List accepted assignments for an assignment
  • classroom/get-assignment-grades (GET /assignments/{assignment_id}/grades) — read — Get assignment grades
  • classroom/list-classrooms (GET /classrooms) — read — List classrooms
  • classroom/get-a-classroom (GET /classrooms/{classroom_id}) — read — Get a classroom
  • classroom/list-assignments-for-a-classroom (GET /classrooms/{classroom_id}/assignments) — read — List assignments for a classroom
  • codes-of-conduct/get-all-codes-of-conduct (GET /codes_of_conduct) — read — Get all codes of conduct
  • codes-of-conduct/get-conduct-code (GET /codes_of_conduct/{key}) — read — Get a code of conduct
  • credentials/revoke (POST /credentials/revoke) — write — Revoke a list of credentials
  • emojis/get (GET /emojis) — read — Get emojis
  • actions/get-actions-cache-retention-limit-for-enterprise (GET /enterprises/{enterprise}/actions/cache/retention-limit) — read — Get GitHub Actions cache retention limit for an enterprise
  • actions/set-actions-cache-retention-limit-for-enterprise (PUT /enterprises/{enterprise}/actions/cache/retention-limit) — write — Set GitHub Actions cache retention limit for an enterprise
  • actions/get-actions-cache-storage-limit-for-enterprise (GET /enterprises/{enterprise}/actions/cache/storage-limit) — read — Get GitHub Actions cache storage limit for an enterprise
  • actions/set-actions-cache-storage-limit-for-enterprise (PUT /enterprises/{enterprise}/actions/cache/storage-limit) — write — Set GitHub Actions cache storage limit for an enterprise
  • oidc/list-oidc-custom-property-inclusions-for-enterprise (GET /enterprises/{enterprise}/actions/oidc/customization/properties/repo) — read — List OIDC custom property inclusions for an enterprise
  • oidc/create-oidc-custom-property-inclusion-for-enterprise (POST /enterprises/{enterprise}/actions/oidc/customization/properties/repo) — write — Create an OIDC custom property inclusion for an enterprise
  • oidc/delete-oidc-custom-property-inclusion-for-enterprise (DELETE /enterprises/{enterprise}/actions/oidc/customization/properties/repo/{custom_property_name}) — destructive — Delete an OIDC custom property inclusion for an enterprise
  • code-security/get-configurations-for-enterprise (GET /enterprises/{enterprise}/code-security/configurations) — read — Get code security configurations for an enterprise
  • code-security/create-configuration-for-enterprise (POST /enterprises/{enterprise}/code-security/configurations) — write — Create a code security configuration for an enterprise
  • code-security/get-default-configurations-for-enterprise (GET /enterprises/{enterprise}/code-security/configurations/defaults) — read — Get default code security configurations for an enterprise
  • code-security/get-single-configuration-for-enterprise (GET /enterprises/{enterprise}/code-security/configurations/{configuration_id}) — read — Retrieve a code security configuration of an enterprise
  • code-security/update-enterprise-configuration (PATCH /enterprises/{enterprise}/code-security/configurations/{configuration_id}) — write — Update a custom code security configuration for an enterprise

Read the full file on GitHub · 110 lines

Changes

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.

  1. yesterday First seen · 110 lines · 33 tokens per session scan A 05357677a887

Subscribe to this mod's changes

github is a skill published in the GitHub repository JustVugg/tools-factory (51 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,978 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Orchestra-Research/AI-Research-SKILLs · 68 tokens

taiyi-ui-design

TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.

Dong90/oh-my-taiyiforge · 35 tokens