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/openshift-eng/ai-helpersWrote 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/openshift-eng/ai-helpers/prune-update)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/prune-update"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/prune-update/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/openshift-eng/ai-helpers/prune-update"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/prune-update.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 | $0.00023 | $0.02154 |
| Opus 5.5 | $0.00009 | $0.00862 |
| Sonnet 5.5 | $0.00005 | $0.00431 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade C, and why
prune-update scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
git rm -rf {path} How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
marketplace-ops:prune-update
Synopsis
/marketplace-ops:prune-update [PR number or URL]
Description
Reads comments on a pruning PR to find /save <path> and /drop <path> directives.
For each saved item:
- Restores the files from the base branch.
- Adds the path to
.pruneprotectpermanently, with a comment noting who requested it and when. - Pushes a new commit to the PR branch (never force-pushes).
- Updates the PR body to mark saved items.
For each dropped item:
- If the item was previously
/saved: removes its files again, removes it from.pruneprotect. - If the item is a new addition (not in the original manifest): removes its files and adds a new row to the manifest.
- For surviving plugins that lose commands or skills, bumps the patch version in
plugin.json. - Pushes a new commit to the PR branch (never force-pushes).
- Updates the PR body to reflect the drop.
Arguments
$1: (Optional) PR number or URL. If omitted, searches for the most recent open pruning PR by the current user.
Implementation
Step 1: Find the Pruning PR
If a PR number or URL was provided, use it directly. Otherwise, find the most recent open pruning PR:
gh pr list --author="@me" --state=open --search="prune stale marketplace" --json number,title,url,headRefName --limit 5
Select the first result. If no pruning PR is found, report this to the user and stop.
Step 2: Read PR Comments for /save and /drop Directives
Fetch all comments on the PR (both issue comments and review comments), including the author's association to the repository:
# Issue comments
gh api repos/{owner}/{repo}/issues/{pr_number}/comments \
--jq '.[] | {id: .id, created_at: .created_at, author: .user.login, association: .author_association, body: .body}'
# Review comments
gh api repos/{owner}/{repo}/pulls/{pr_number}/comments \
--jq '.[] | {id: .id, created_at: .created_at, author: .user.login, association: .author_association, body: .body}'
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 · 245 lines · 23 tokens per session scan C 7b937f3e1ea9
prune-update is a command published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 2,154 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other commands, from other repositories
standup
Review my git commits from the past workday and generate a standup summary.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
commit
Context-aware Git commit assistant with smart pre-commit checks.