A command-line skill for working with GitHub, the code-hosting service, through authenticated commands for repositories, issues, pull requests, releases, checks, and searches.

Use it to create, view, update, close, comment on, or merge issues and pull requests, inspect repositories and checks, and search GitHub.

It provides one standard route for common GitHub operations and can use the current repository when an owner and repository are not specified.

github-cli — Skill by Tracer-Cloud

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/tracer-cloud/opensre/github_cli

Any agent

npx skills add Tracer-Cloud/opensre --skill github_cli

Clone the repo

git clone --depth 1 https://github.com/Tracer-Cloud/opensre

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 605 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.

Model	Per session	Once invoked
Fable 5	$0.00072	$0.00605
Opus 5	$0.00036	$0.00302
Sonnet 5	$0.00014	$0.00121
Haiku 4.5	$0.00007	$0.00060

Measured yesterday against content hash 24b0196b5a38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-cli 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.

The scan reads SKILL.md. This mod also ships 5 executable files (__init__.py, credentials.py, runner.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

integrations/github/tools/github_cli/SKILL.md · 50 lines

What it actually says

github-cli

Authenticated gh for OpenSRE. Reads and writes — no approval gate. Prefer over shell_run / !gh. Pass args after gh; optional repo as owner/name → -R. Blocked top-level: auth, extension, workflow, run, secret, codespace, ssh-key, gpg-key, config.

Capabilities

Intent	Example `args`
Create issue	`["issue", "create", "--title", "…", "--body", "…"]`
List / view issues	`["issue", "list"]` / `["issue", "view", "42"]`
Close / comment / edit	`["issue", "close", "42"]` / `["issue", "comment", "42", "--body", "…"]`
List / view / close / merge PRs	`["pr", "list"]` / `["pr", "view", "45"]` / `["pr", "close", "45"]` / `["pr", "merge", "45"]`
Repos / search	`["repo", "list"]` / `["search", "issues", "crash"]`
Arbitrary API	`["api", "repos/OWNER/REPO/issues"]`

After github_cli returns

Use summary when present. Reply short and chat-like.

Simple (create/close/comment/merge, URL/#n): plain prose, one sentence.
Structured reads: light chat markdown — short lead-in + bullets (* #42 — title); no tables/headers.
Mutate extras: at most 2–4 bullets. No GraphQL/JSON dumps. No "I found:".
Failure: one sentence from error / error_type — say it failed to run.

Prefer dedicated tools when they clearly fit

Slack propose/execute; workflow digests; investigation code/commit search. Multi-source RCA (sentry + github issues + posthog) → investigation_start. PR CI fix-and-push → fix_github_pr_ci. Security/quality alerts → fix_github_security_alert.

Limitations

gh on PATH; OpenSRE token auth. Action-only — not in gather/investigation.

Files

What ships with it

5 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.

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.

yesterday First seen · 50 lines · 72 tokens per session scan A 24b0196b5a38

Subscribe to this mod's changes

github-cli is a skill published in the GitHub repository Tracer-Cloud/opensre (10,969 stars, last pushed 2d ago), licensed Apache-2.0. It adds 72 tokens to every session and 605 once invoked, about $0.0004 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.

Backend and APIs Debugging Git and workflow ai-sre alerting datadog grafana observability remediation

github-cli

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

github-cli

Capabilities

After github_cli returns

Prefer dedicated tools when they clearly fit

Limitations

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

host_bash

host_restart_service

file_inspector

edge_disk_audit

future_skill

pwned