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.
git clone --depth 1 https://github.com/sfc-gh-eraigosa/dotfilesWrote 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/sfc-gh-eraigosa/dotfiles/gss-pr)<a href="https://agentmods.dev/commands/sfc-gh-eraigosa/dotfiles/gss-pr"><img src="https://agentmods.dev/badge/commands/sfc-gh-eraigosa/dotfiles/gss-pr/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/commands/sfc-gh-eraigosa/dotfiles/gss-pr"><img src="https://agentmods.dev/badge/commands/sfc-gh-eraigosa/dotfiles/gss-pr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.00618 |
| Opus 5 | $0.00006 | $0.00309 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
gss-pr 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 9d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are about to run the gss pr workflow (creates a feature branch, pushes, opens a PR on GitHub).
Current state
!gss status
Pending diff
!git diff --stat
Arguments (PR title hint, optional): $ARGUMENTS
Follow the git-safe-sync skill rules strictly:
- Summarize what would be pushed and what the PR will contain.
- STOP. Do NOT execute
gss pruntil the user explicitly confirms in a follow-up turn. - On confirmation, commit any pending changes first, then run the token +
gss prpair.gss prnever commits — with uncommitted changes and nothing ahead oforigin/mainit now fails fast with "nothing to PR" (and on older binaries it pushed an empty branch and died ongh pr create). Sequence, as separate Bash calls (chaining them with&&is intentionally blocked bysafety_guard.sh):- Call 1 (only if the diff above shows pending changes): stage by explicit file name (never
git add -A) and commit with a HEREDOC message. - Call 2:
mkdir -p ~/.config/gss && git rev-parse HEAD > ~/.config/gss/approval.token(the token is HEAD-bound — always generate it AFTER the commit) - Call 3:
gss pr --title "<subject>" --body "<markdown body>"Per the skill's PR Hygiene rule you MUST pass a real--body(What/Why/Impact/Testing);gss prdoes not infer one, so omitting it ships an empty description. (gss prhas no--draftflag; classic PRs are created ready-for-review.) - Updating an existing PR: if the branch already has an open PR and you are pushing more commits,
gss pr/gss pushwill NOT refresh the body — you MUST update it yourself withgh pr edit <number> --title/--bodyso the description reflects every commit now on the PR. Never leave a stale description behind a push.
- Call 1 (only if the diff above shows pending changes): stage by explicit file name (never
- After execution, surface the PR URL prominently. If you updated an existing PR, confirm its description was refreshed to match. Then ask whether to open it via the
open-url <url>helper (opt/scripts/misc/open-url) — it picks the right opener per platform (macOSopen, WSLwslview/explorer.exe, Linuxxdg-open).
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.
- 9d ago First seen · 29 lines · 13 tokens per session scan A f011c9f2bc59
gss-pr is a command published in the GitHub repository sfc-gh-eraigosa/dotfiles (46 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 618 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
pr-review
Intelligent PR code review with dynamic agent allocation based on change types.
merge-dependabot
@source https://github.com/trailofbits/claude-code-config @description Evaluate and merge dependabot PRs with parallel builds, dependency-aware batching, and transitive dep analysis. @arguments $REPO: GitHub org/repo (e.g., trailofbits/algo). $OPTIONS: Optional flags — "--skip-config-audit" skips Phase 0 (use in batch…
pr-address-reviews
Address unresolved review comments on PR $ARGUMENTS.
commit
Follow the Commit messages rule in the repository AGENTS.md when present; otherwise use the Conventional Commits 1.0.0 summary below.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes. Invoke with /create-pr.
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits. Invoke with /scan-commit.