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 skills add Arakiss/galdr --skill galdr-demogit clone --depth 1 https://github.com/Arakiss/galdrWrote 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/skills/arakiss/galdr/galdr-demo)<a href="https://agentmods.dev/skills/arakiss/galdr/galdr-demo"><img src="https://agentmods.dev/badge/skills/arakiss/galdr/galdr-demo/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/skills/arakiss/galdr/galdr-demo"><img src="https://agentmods.dev/badge/skills/arakiss/galdr/galdr-demo.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 | $0.00061 | $0.00496 |
| Opus 5.5 | $0.00024 | $0.00198 |
| Sonnet 5.5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
galdr-demo 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 1mo 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.
What it actually says
galdr-demo — git change summary to a file
Collects a git repository's status and latest commits and dumps them as a readable Markdown summary. Distilled with galdr from a real recording.
Goal
Given a git repository, produce a short Markdown file describing what changed: the uncommitted working tree (status) and the latest commits (log). It serves as a quick change note without opening the repo.
Parameters
REPO— path to the git repository. Defaults to the current working directory.OUT— path of the output Markdown file.N— number of commits to include (5 in the recording).
Procedure
-
Working tree status:
git -C <REPO> status --short. If the output is empty, there are no uncommitted changes; note that in the summary. -
Latest commits:
git -C <REPO> log --oneline -<N>. -
Write the summary to
<OUT>in this shape:# Recent changes ## Uncommitted <status output, or "(clean tree)"> ## Latest N commits <log output> -
Verify: read
<OUT>and check it has content (it did not come out empty).
Success criteria
- Both git commands exit with code 0. If
<REPO>is not a git repo, both fail: abort with a clear message. <OUT>exists and contains the two sections with real repo data.
Robustness
- Precondition:
<REPO>must be a git repository. Check it withgit -C <REPO> rev-parsebefore steps 1-2. - If
logfails because the repo has no commits yet, write "(no commits yet)" in that section instead of aborting. - Do not include absolute paths with sensitive data if you are going to share the summary.
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.
- 1mo ago First seen · 56 lines · 61 tokens per session scan A 27478c2c9017
galdr-demo is a skill published in the GitHub repository Arakiss/galdr (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 496 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
oz-report-pr
Report a pull request back to the Oz platform after creating one.
git
Run git version control commands for repository management. Use when the user asks to check status, view history or diffs, stage and commit changes, manage branches, merge or rebase, work with remotes, stash changes, tag releases, cherry-pick commits, bisect regressions, resolve conflicts, manage worktrees or…
pdf-documents
Generate PDFs with fpdf2 and merge, split, or fill existing PDFs with pypdf, with visual QA before delivery.
git-commits-and-prs
Load BEFORE creating a git commit or a GitHub pull request. Step-by-step protocol for drafting commit messages, staging safely, amend rules, and gh pr create choreography.
reviewing-pull-requests
Review GitHub pull requests and triage open PRs and issues: classify blast radius, decide review versus close, and draft evidence-linked comments. Use when the user asks to review a PR, triage a PR queue, roast a change, decide whether a stale PR still matters, or address open review comments — even when they only…