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 commands/sgaunet/claude-plugins/gen-forgejo-dirgit clone --depth 1 https://github.com/sgaunet/claude-pluginsWrote 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/commands/sgaunet/claude-plugins/gen-forgejo-dir)<a href="https://agentmods.dev/commands/sgaunet/claude-plugins/gen-forgejo-dir"><img src="https://agentmods.dev/badge/commands/sgaunet/claude-plugins/gen-forgejo-dir.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.07478 |
| Opus 5 | $0.00015 | $0.03739 |
| Sonnet 5 | $0.00006 | $0.01496 |
| Haiku 4.5 | $0.00003 | $0.00748 |
Grade A, and why
gen-forgejo-dir 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 4d 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 — 667 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate .forgejo Directory Command
Instantly create a complete .forgejo/workflows directory structure for Go projects with production-ready, mise-based Forgejo Actions workflows (linting, coverage, snapshot builds, releases).
Forgejo Actions reuses GitHub-Actions-compatible workflow syntax, so the workflow content is identical to what /gen-github-dir produces. The key differences are the directory location (.forgejo/workflows/ instead of .github/workflows/), the runs-on runner label, and the action/registry source assumptions described below.
Like the GitHub variant, the workflows install tooling via jdx/mise-action@v3 and run task …, so CI uses the exact tool versions pinned in mise.toml (created at the repo root if missing). This also shrinks the set of GitHub actions that must be mirrored on your instance to just actions/checkout and jdx/mise-action.
Why This Command Exists
Problem: Setting up CI/CD for Go projects on a Forgejo instance requires manually creating multiple workflow files, understanding that Forgejo Actions mirrors GitHub Actions syntax but lives under a different directory, and wiring up runner labels - a 30-60 minute process.
Solution: One-command generation that:
- Creates a complete
.forgejo/workflowsdirectory structure - Includes comprehensive workflows: linting, coverage, snapshot builds, releases
- Targets a Forgejo Actions runner label (not
ubuntu-latest) - Preserves all customization comments for user control
Forgejo Actions Assumptions
This command makes the following assumptions about your Forgejo instance. Review them before running:
- Runner label — Workflows are generated with
runs-on: docker(a common default label for the official Forgejo Actions runner). You must have at least one registered Forgejo Actions runner that advertises this label. Manage runners with the Forgejo CLI:
If your runner uses a different label (e.g.fgj actions runner list # List registered runners and their labels fgj actions runner register # Register a new runnerself-hosted,ubuntu-latest, or a custom label), editruns-on:in the generated files or re-run after adjusting your runner registration. Without a matching registered runner, workflows will queue forever.
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.
- 4d ago First seen · 667 lines · 29 tokens per session scan A 638c4e5cb9b0
gen-forgejo-dir is a command published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 7,478 once invoked, about $0.0001 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.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.