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 agentmods add skills/mountainunicorn/add/backnpx skills add MountainUnicorn/add --skill backgit clone --depth 1 https://github.com/MountainUnicorn/addWhat 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 | $0.00016 | $0.00615 |
| Opus 5 | $0.00008 | $0.00308 |
| Sonnet 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 2d 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.
- 2d 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 1mo ago), licensed MIT. It adds 16 tokens to every session and 615 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 skills, from other repositories
taiyi-plan
TaiyiForge /taiyi:plan — 项目规划入口:把 README/PRD 拆解为独立 change 清单,推荐 profile 和依赖关系。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-task
TaiyiForge 第5阶段 — 任务拆解,TASK.md。四端通用。.
taiyi-ultrawork
TaiyiForge ultrawork — 并行切片 + Cursor Task 自动派发契约(对标 OMC ultrawork + spawnagent).
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…
triage
Work-unit triage for GitHub issues. Groups raw issues, fuses each group with the AGENTS.md northstar, and externalizes each routed unit to a substrate record a collaborator session is pointed at.
github-issue-manager
Classifies a user request as Bug, Compatibility, Feature, Question, or Task for the explyt/spring-plugin GitHub repo, lightly researches the relevant codebase, searches similar existing issues, and either reports an existing issue or creates a correctly titled and labeled one following the repository issue forms. Use…