fj

fj is a skill for Claude Code, Codex from natsukium/dotfiles. It costs 58 tokens per session (1,557 once invoked), scanned A, original, CC0-1.0.

A command-line tool for managing Forgejo, a Git hosting service, on git.natsukium.com. It works with repositories, issues, pull requests, releases, Actions, organizations, and users.

In plain words
What is it for?
Use it to search and view issues, manage pull requests, work with repositories and releases, and operate Forgejo Actions on that host.
Why use it?
It provides the appropriate commands for that Forgejo server instead of treating it like a different hosting service. It also helps agents identify the repository and server explicitly in automated commands.

Skill for Claude CodeCodex

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

Good fit Use it to search and view issues, manage pull requests, work with repositories and releases, and operate Forgejo Actions on that host.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/natsukium/dotfiles/fj
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 natsukium/dotfiles --skill fj
Clone the repo
git clone --depth 1 https://github.com/natsukium/dotfiles

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 fj

README.md
[![agentmods](https://agentmods.dev/badge/skills/natsukium/dotfiles/fj.svg)](https://agentmods.dev/skills/natsukium/dotfiles/fj)
Your own site
<a href="https://agentmods.dev/skills/natsukium/dotfiles/fj"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/fj.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,557 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 39
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00058 $0.01557
Opus 5 $0.00029 $0.00779
Sonnet 5 $0.00012 $0.00311
Haiku 4.5 $0.00006 $0.00156

Measured today against content hash 831e5ae32057, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fj 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.

modules/features/coding-agents/common/skills/fj/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fj - Forgejo CLI

Use fj for Forgejo-specific operations on git.natsukium.com. Use git for local commits, branches, and pushes.

Select the host and repository explicitly

For unattended commands, avoid checkout inference and provide both the public host and repository:

fj -H https://git.natsukium.com issue search --repo owner/repo
fj -H https://git.natsukium.com issue view 'owner/repo#42'

Repository syntax depends on the command:

  • Collection and create commands for issues and PRs accept --repo owner/repo.
  • Commands acting on an existing issue accept a positional qualified reference such as 'owner/repo#42'.
  • Most commands acting on an existing PR accept the same qualified form. pr assign and pr unassign take it through --pr instead.
  • Repository commands generally take owner/repo as a positional argument. Releases, tags, Actions, and wikis expose their own global --repo; check the relevant --help before composing less common commands.
  • Convert a URL such as https://git.natsukium.com/owner/repo/issues/42 or /pulls/42 to 'owner/repo#42'.

-C, -R, and the current directory infer the instance and repository from a Git remote. Prefer -H with --repo (or a qualified reference) over -R for unattended commands: -R resolves the named remote and takes precedence over -H, and an SSH remote host is resolved through OpenSSH config, so a HostName rewrite to the internal host makes fj dial https:// on a host that does not serve it. If a command fails against the internal host, retry with -H https://git.natsukium.com and an explicit repository or qualified reference instead of connecting Tailscale; reserve -R for deliberate checkout inference.

Authentication

fj auth list
fj -H https://git.natsukium.com whoami
fj auth login -H https://git.natsukium.com
fj auth add-token -H https://git.natsukium.com  # reads the token from stdin when omitted
fj auth logout -H https://git.natsukium.com

fj auth list should include git.natsukium.com. Never print or place an access token directly in a recorded command.

Read the full file on GitHub · 103 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. today Changed · +3 lines 831e5ae32057
  2. yesterday First seen · 100 lines · 58 tokens per session scan A 6fd367033bc3

Subscribe to this mod's changes

fj is a skill published in the GitHub repository natsukium/dotfiles (103 stars, last pushed today), licensed CC0-1.0. It adds 58 tokens to every session and 1,557 once invoked, about $0.0003 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 2026-09-06.

Related

Other skills, from other repositories

ship

Verify and publish by pushing, opening a PR, and watching CI; land mode merges then cleans branches. Triggers "ship it", "create PR", "/ship", "watch the PR", "babysit CI"; land mode "land it", "/ship land", "fix CI and merge".

darkroomengineering/cc-settings · 63 tokens

github-workflow

Professional GitHub issue/PR workflow with gh CLI. Use when a best-practice use case needs issue → PR → Closes.

mamahoos/dot-files · 30 tokens

release

Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.

fmind/dotfiles · 40 tokens

sync-release

Owns release-pipeline conventions: sr.yaml schema, the sr CLI verbs (init/plan/prepare/ release) and urmzd/sr action, typed publishers (cargo/npm/pypi/docker/go/custom), monorepo workspace discovery, versionfiles/stagefiles mapping, and post-release patterns. Language-specific build targets live in scaffold-rust…

urmzd/dotfiles · 136 tokens

setup-ci

Defines GitHub Actions workflow structure: ci.yml + release.yml naming, concurrency groups, bot-commit skip, workflowcall reuse, App-token checkout, and optional fsrc/teasr steps. Language-specific pipelines live in scaffold-rust, scaffold-go, scaffold-python, scaffold-node, scaffold-terraform. Use when setting up…

urmzd/dotfiles · 119 tokens

release-audit

Audit GitHub releases, git tags, and release assets for one repo or every repo in a directory. Flags orphaned tags, missing binaries/checksums, draft releases, floating tag drift, pre-release remnants, and (when sr.yaml is present) sr config issues. Read-only: never deletes or modifies tags/releases. Use when checking…

urmzd/dotfiles · 126 tokens