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 MountainUnicorn/add --skill backgit clone --depth 1 https://github.com/MountainUnicorn/addWrote 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/mountainunicorn/add/back)<a href="https://agentmods.dev/skills/mountainunicorn/add/back"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/back/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/mountainunicorn/add/back"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/back.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 | $0.00016 | $0.00615 |
| Opus 5.5 | $0.00006 | $0.00246 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
back 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADD Back Command v{{VERSION}}
The human has returned. Provide a concise briefing on what happened during their absence.
Phase 1: Gather Status
- Read
.add/away-log.mdfor the work log - Read
.add/handoff.mdif it exists — note in-progress work, decisions, blockers, and next steps from the last session - Read
.add/swarm-state.mdif it exists — note any parallel agent work that was active, completed, or blocked - Read
.add/decisions.mdif it exists — note any architectural decisions made during absence - Check git log for commits made during the away period
- Run test suite to get current status
- Check for any pending quality gate issues
- Read TodoWrite for current task state
Phase 2: Compile Briefing
Welcome back. Here's what happened while you were away.
DURATION: {actual time elapsed}
COMPLETED:
━━━━━━━━━
{for each completed task:}
✓ {task description}
Tests: {N passing} | Spec: {AC-IDs covered}
Commits: {commit hashes}
IN PROGRESS:
━━━━━━━━━━
{any task that was started but not finished:}
◐ {task description}
Status: {where it stands}
Blocker: {if any}
NEEDS YOUR INPUT:
━━━━━━━━━━━━━━━
{numbered list of decisions queued during absence:}
1. {decision description}
Options: {A vs B vs C}
2. {decision description}
COORDINATION STATE:
━━━━━━━━━━━━━━━━━
Handoff: {summary of handoff.md — in-progress items and next steps, or "no handoff file"}
Swarm: {summary of swarm-state.md — active/completed/blocked agents, or "no active swarm"}
Decisions: {N new decisions logged, or "no new decisions"}
CURRENT PROJECT STATE:
━━━━━━━━━━━━━━━━━━━━
Tests: {N passing}, {N failing}, {N skipped}
Coverage: {N}%
Lint: {clean/N issues}
Types: {clean/N issues}
Branch: {current branch}
Uncommitted changes: {yes/no}
Phase 3: Clean Up
- Archive
.add/away-log.mdto.add/away-logs/away-{timestamp}.md(mkdir -p first) - Update TodoWrite with current state
Phase 4: Re-Engage
Ask: "What would you like to focus on first?"
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 · 77 lines · 16 tokens per session scan A ff14e916e861
back is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 615 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 2026-08-30.
Other skills, from other repositories
triage
Triage insights into actionable GitHub issues across repos. Use after running /insights to convert analysis into tracked work.
ticket
Associate every PDS task with a GitHub issue. Orchestrator finds or creates the ticket, posts plan and acceptance criteria as a checkbox list, updates it as work progresses. Use at Phase 1 of every swarm.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
bmad-agent-pm
Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.