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/mdsakalu/agent-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/mdsakalu/agent-plugins/ref)<a href="https://agentmods.dev/commands/mdsakalu/agent-plugins/ref"><img src="https://agentmods.dev/badge/commands/mdsakalu/agent-plugins/ref/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/mdsakalu/agent-plugins/ref"><img src="https://agentmods.dev/badge/commands/mdsakalu/agent-plugins/ref.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 | $0.00727 |
| Opus 5.5 | $0.00005 | $0.00291 |
| Sonnet 5.5 | $0.00003 | $0.00145 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
ref 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a reference (PR, Jira ticket) to the current workspace.
Resolve the metarepo path by reading ~/.claude/workspace-config.json and expanding ~ to $HOME.
The user's request: $ARGUMENTS
Steps
- Read
~/.claude/workspace-config.jsonto get the metarepo path. Expand~to$HOME. - Determine the current workspace:
- Infer from cwd: match
*/repos/<repo>/<workspace>*to extract repo and workspace - Or use
.workspace.jsonsymlink if it exists in cwd - If unable to determine, ask the user
- Infer from cwd: match
- Read
<metarepo>/notes/<repo>/<workspace>/workspace.json(or via.workspace.jsonsymlink). - Read
<metarepo>/repos/<repo>/.repo.jsonfor GitHub owner/repo info. - Parse the user's input for the reference:
- PR:
#1234,1234,PR #1234, or a full GitHub PR URL - Jira ticket:
PROJ-1234,TEAM-123,WORK-456(uppercase project key + dash + number)
- PR:
- For PR references:
- Resolve full URL using .repo.json:
https://github.com/<owner>/<repo>/pull/<number> - Get PR title:
gh pr view <number> --json title -q '.title' --repo <owner>/<repo> - Capture JJ change ID:
jj log -r @ --no-graph -T change_id(from workspace directory) - Capture branch:
jj log -r @ --no-graph -T 'bookmarks' - Check for duplicates in workspace.json references
- Append to references array using jq:
jq --arg url "$URL" --argjson num $NUMBER --arg change_id "$CHANGE_ID" --arg branch "$BRANCH" --arg added "$(date +%Y-%m-%d)" \ '.references += [{"type":"pr","number":$num,"url":$url,"jj_change_id":$change_id,"branch":$branch,"added":$added}]' \ workspace.json > tmp && mv tmp workspace.json
- Resolve full URL using .repo.json:
- For Jira references:
- Check for duplicates
- Append using jq:
jq --arg key "$KEY" --arg added "$(date +%Y-%m-%d)" \ '.references += [{"type":"jira","key":$key,"added":$added}]' \ workspace.json > tmp && mv tmp workspace.json
- Confirm what was added and show the updated references.
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 · 53 lines · 13 tokens per session scan A ff5c60f9b658
ref is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 727 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
land
Resolve and squash merge one named, currently authorized pull request.
standup
Review my git commits from the past workday and generate a standup summary.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
sync
Synchronizes your local swarm state with the latest GitHub repository state, updating task statuses and detecting changes.
claim
Claims a GitHub issue for your swarm to work on, preventing conflicts with other swarms.