Commonly is a self-hosted collaborative workspace where people work with multiple AI agents, each retaining its own name, memory, skills, and workstation. Teams use it to assign and refine real work across different agent runtimes, and the catalogue entries supply agents, skills, and instructions for use in those rooms.
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 Team-Commonly/commonly --skill githubgit clone --depth 1 https://github.com/Team-Commonly/commonlyWrote 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/team-commonly/commonly/github)<a href="https://agentmods.dev/skills/team-commonly/commonly/github"><img src="https://agentmods.dev/badge/skills/team-commonly/commonly/github/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/team-commonly/commonly/github"><img src="https://agentmods.dev/badge/skills/team-commonly/commonly/github.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 | $0.00049 | $0.00952 |
| Opus 5.5 | $0.00020 | $0.00381 |
| Sonnet 5.5 | $0.00010 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
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 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
github — GitHub via the gh CLI
The gh CLI is installed on PATH. The gateway environment provides a
GITHUB_PAT env var (a Team-Commonly fine-grained PAT with repo + PR scope)
which gh picks up automatically as GH_TOKEN.
The active GitHub identity is Team-Commonly bot identity — anything you push, comment, or open will be attributed to that account.
No shell? Don't use
gh. Theghexamples below assume a real shell (codex / claude-code runtimes). OpenClaw runtimes (theo/nova/pixel/ops) have no shell and cannot runghat all. For those agents:
- Read a PR diff:
web.fetchthe raw public diff athttps://patch-diff.githubusercontent.com/raw/Team-Commonly/commonly/pull/<N>.diff.- Post a review verdict: write it into the dev pod chat (read-only review).
- codex / claude-code runtimes have a shell: use
ghdirectly, as below.There is deliberately no
commonly_pr_*MCP tool. The pair that existed was removed because it spent a shared server-side credential on a caller-chosen repository, so any agent could review any repo that credential reached.ghacts as the machine's own GitHub identity and supports line-level comments, which those tools never did.
Common operations
Issues
# List open issues in a repo
gh issue list --repo Team-Commonly/commonly --state open
# Create an issue
gh issue create --repo Team-Commonly/commonly \
--title "Title here" \
--body "Body here"
# Comment on an issue
gh issue comment 123 --repo Team-Commonly/commonly --body "comment"
Pull requests
# List open PRs
gh pr list --repo Team-Commonly/commonly --state open
# View a PR (diff, comments, status)
gh pr view 287 --repo Team-Commonly/commonly --json title,body,additions,deletions
# Get a PR's diff
gh pr diff 287 --repo Team-Commonly/commonly
# Comment on a PR
gh pr comment 287 --repo Team-Commonly/commonly --body "comment text"
# Check CI status
gh pr checks 287 --repo Team-Commonly/commonly
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 · 112 lines · 49 tokens per session scan A 804a70811466
github is a skill published in the GitHub repository Team-Commonly/commonly (1,363 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 952 once invoked, about $0.0002 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
release
Cut and maintain Observal release branches, prepare alpha, beta, RC, stable, and patch releases, backport merged main PRs, inspect release status, verify published artifacts, and recover failed release operations. Use for Observal maintainer release tasks and release-process changes, not for installing or upgrading an…
git-expert
Git operations expert for branching, rebasing, conflicts, and workflows.
github
GitHub operations expert for PRs, issues, code review, Actions, and gh CLI.
flag-cleanup
Weekly reusable-session feature-flag cleanup for {{targetrepo}}. Inventories every feature flag, classifies each as fully rolled out, long dead, partial rollout, or active experiment, removes the flag and the dead branch it guards on an isolated branch when the suite is green, and opens a PR — never touching a flag…
changelog-sync
Reusable-session release-notes runbook for {{targetrepo}}. Finds the range since the last release covered, reads every PR merged in it, groups them by area, writes plain-language notes in the house voice, and opens a PR against {{changelogpath}} only when a new release has actually shipped.
flaky-test-quarantine
Daily reusable-session flaky-test triage for {{targetrepo}}. Pulls CI run history from GitHub, scores each test's non-determinism against a persistent per-test ledger, and once a test reaches {{quarantinethreshold}} opens a quarantine PR (skip + reason, never delete) plus a running tracking issue, and posts a summary…