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/imoonkey/openweb/githubnpx skills add imoonkey/openweb --skill githubgit clone --depth 1 https://github.com/imoonkey/openwebWhat 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 | $0.00000 | $0.01549 |
| Opus 5 | $0.00000 | $0.00775 |
| Sonnet 5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
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 2d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub
Overview
GitHub REST + GraphQL API — code hosting platform (developer tools archetype).
Workflows
Explore a repository
searchRepos(q)→ pick result →owner,repofromfull_namegetRepo(owner, repo)→ description, stars, languagegetRepoReadme(owner, repo)→ base64-encoded README contentlistIssues(owner, repo)→ open issueslistPullRequests(owner, repo)→ open PRs
Investigate a user's work
getUserProfile(username)→ bio, public_repos, followerssearchRepos(q: "user:username")→ their repositories
File an issue
searchRepos(q)→owner,repofromfull_name(or use known repo)createIssue(owner, repo, title, body)→number,html_url
Manage issues
listIssues(owner, repo)→issue_number,title,statecloseIssue(owner, repo, issue_number ← listIssues)→state: "closed"reopenIssue(owner, repo, issue_number ← listIssues)→state: "open"createComment(owner, repo, issue_number ← listIssues, body)→comment_id,html_urldeleteComment(owner, repo, comment_id ← createComment)→ 204
Star / watch a repo
searchRepos(q)→owner,repofromfull_namestarRepo(owner, repo)→ 204unstarRepo(owner, repo)→ 204watchRepo(owner, repo)→subscribedunwatchRepo(owner, repo)→ 204
Operations
| Operation | Intent | Key Input | Key Output | Notes |
|---|---|---|---|---|
| searchRepos | find repositories | q | total_count, items[].full_name, stargazers_count, language | entry point, paginated |
| getRepo | repository details | owner, repo | full_name, description, stargazers_count, forks_count, language | entry point |
| getUserProfile | user profile | username | login, name, bio, public_repos, followers, following | entry point |
| getRepoReadme | repository README | owner ← getRepo, repo ← getRepo | name, content (base64), encoding | |
| listIssues | repository issues | owner ← getRepo, repo ← getRepo | number, title, state, user.login, labels | paginated |
| listPullRequests | repository PRs | owner ← getRepo, repo ← getRepo | number, title, state, user.login, head.ref, base.ref | paginated |
| listContributors | repository contributors | owner ← getRepo, repo ← getRepo | login, contributions | paginated |
| createIssue | create an issue | owner ← getRepo, repo ← getRepo, title, body | number, html_url | write, CAUTION |
| closeIssue | close an issue | owner, repo, issue_number ← listIssues | data (GraphQL response) | write, CAUTION. Routes through github.com /_graphql |
| reopenIssue | reopen a closed issue | owner, repo, issue_number ← listIssues | data (GraphQL response) | write, CAUTION — reverse of closeIssue. Routes through github.com /_graphql |
| createComment | comment on issue/PR | owner, repo, issue_number ← listIssues, body | id, body, html_url | write, CAUTION |
| deleteComment | delete a comment | owner, repo, comment_id ← createComment | — (204) | write, CAUTION — reverse of createComment |
| forkRepo | fork a repository | owner ← getRepo, repo ← getRepo | full_name | write, CAUTION |
| starRepo | star a repository | owner ← getRepo, repo ← getRepo | — (204) | write, SAFE. (api.github.com — currently rejected by cookie_session, see DOC.md) |
| unstarRepo | unstar a repository | owner ← getRepo, repo ← getRepo | count (watcher count) | write, CAUTION — reverse of starRepo. Routes through github.com rails endpoint |
| watchRepo | watch a repository | owner ← getRepo, repo ← getRepo | count (watcher count) | write, CAUTION. Routes through github.com /notifications/subscribe |
| unwatchRepo | unwatch a repository | owner ← getRepo, repo ← getRepo | count (watcher count) | write, CAUTION — reverse of watchRepo. Routes through github.com /notifications/subscribe |
| graphqlQuery | execute GraphQL | query, variables | data | write (unrestricted mutations possible) |
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- adapters/github-read.ts 8.5 KB runs code
- adapters/github-web.ts 15 KB runs code
- DOC.md 9.7 KB
- examples/closeIssue.example.json 319 B
- examples/createComment.example.json 337 B
- examples/createIssue.example.json 409 B
- examples/deleteComment.example.json 261 B
- examples/forkRepo.example.json 271 B
- examples/get_repo.example.json 218 B
- examples/graphqlQuery.example.json 230 B
- examples/list_issues.example.json 236 B
- examples/reopenIssue.example.json 277 B
- examples/starRepo.example.json 272 B
- examples/unstarRepo.example.json 241 B
- examples/unwatchRepo.example.json 242 B
- examples/watchRepo.example.json 237 B
- manifest.json 403 B
- openapi.yaml 32 KB
- PROGRESS.md 6.2 KB
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.
- 2d ago First seen · 95 lines · 0 tokens per session scan A c22acb62d600
github is a skill published in the GitHub repository imoonkey/openweb (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,549 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…