github-repository

github-repository is a skill for Claude Code, Codex from fmind/dot. It costs 19 tokens per session (905 once invoked), scanned A, original, MIT.

A guide for maintaining a GitHub repository’s public details and solo-developer settings from its codebase.

In plain words
What is it for?
Use it to update repository metadata, GitHub Pages links, topics, merge rules, and sidebar features with the GitHub command-line tool.
Why use it?
It avoids manually guessing repository descriptions, topics, homepage links, and merge settings, and keeps those changes repeatable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to update repository metadata, GitHub Pages links, topics, merge rules, and sidebar features with the GitHub command-line tool.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fmind/dot/github-repository
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.

Any agent
npx skills add fmind/dot --skill github-repository
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for github-repository

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/github-repository/github.svg)](https://agentmods.dev/skills/fmind/dot/github-repository)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/github-repository"><img src="https://agentmods.dev/badge/skills/fmind/dot/github-repository/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.

agentmods 80×15 button for github-repository

Your own site · 80×15
<a href="https://agentmods.dev/skills/fmind/dot/github-repository"><img src="https://agentmods.dev/badge/skills/fmind/dot/github-repository.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00019 $0.00905
Opus 5.5 $0.00008 $0.00362
Sonnet 5.5 $0.00004 $0.00181
Haiku 4.5 $0.00002 $0.00090

Measured today against content hash e473f3d406d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-repository 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 today.

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.

skills/github-repository/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Repository

Derive a repository's description, homepage, and topics from its codebase and apply the requested fields with gh repo edit. For a new solo-maintained repository or an explicitly requested settings pass, use the settings baseline; a metadata-only request does not include merge policy, sidebar features, or security settings.

Workflow

Use gh for account selection, repository identity without printing raw remote URLs, bounded API calls, and request serialization when needed.

  1. Extract metadata from the codebase:

    • Project metadata: Python pyproject.toml ([project] name, description, and URLs).
    • README.md: the first paragraphs give a one-line description under ~140 characters.
    • Homepage: use the configured, verified canonical site; do not infer a live Pages site merely from the repository name.
    • Topics: 3 to 6 lowercase tags for language, frameworks, tools, or domain (agent, python, cli); letters, numbers, and hyphens only, 50 characters max, 20 per repository.
  2. Inspect the current state so the edit stays idempotent; stop when there is no GitHub remote or gh is not authenticated:

    state="$(gh repo view --json nameWithOwner,visibility,description,homepageUrl,repositoryTopics)"
    
  3. Build one scoped edit: include only the requested metadata flags; add the desired topics and remove obsolete ones only when replacing the set:

    repository="$(jq -r .nameWithOwner <<<"$state")"
    desired_topics=(tag1 tag2 tag3)
    args=(--description "<description>" --homepage "<homepage-url>")
    for topic in "${desired_topics[@]}"; do args+=(--add-topic "$topic"); done
    while IFS= read -r topic; do
      [[ " ${desired_topics[*]} " == *" $topic "* ]] || args+=(--remove-topic "$topic")
    done < <(jq -r '(.repositoryTopics // [])[].name' <<<"$state")
    
  4. Extend for a settings pass only when settings are in scope: the settings baseline appends merge policy, sidebar features, and secret scanning to the same args, then enables Dependabot security updates, hardens Actions, locks releases, and protects a public repository after the edit.

  5. Apply once with gh repo edit "$repository" "${args[@]}".

  6. Verify with the same gh repo view --json ... fields and report the ones that changed; a settings pass also runs the guide's read-back, which covers fields gh repo view does not expose.

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file 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.

  1. today Changed e473f3d406d3
  2. 3d ago Changed b0b156606392
  3. 7d ago Changed 31c3d852fdbc
  4. 14d ago Changed 0ed4098817bd
  5. 15d ago Changed · -18 lines · -1 tokens per session bd0b6b8df78c
  6. 17d ago Changed · +12 lines 79c9edfd2500
  7. 23d ago Changed 7e95de60f600
  8. 29d ago Changed · -1 lines 30aed9056816
  9. 1mo ago Changed · +3 lines · -17 tokens per session c1c1155a2072
  10. 1mo ago First seen · 70 lines · 37 tokens per session scan A 1536fd19d36a

Subscribe to this mod's changes

github-repository is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 905 once invoked, about $0.0001 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 2026-09-03.