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 saadshahd/moo.md --skill soloflowgit clone --depth 1 https://github.com/saadshahd/moo.mdWrote 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/saadshahd/moo.md/soloflow)<a href="https://agentmods.dev/skills/saadshahd/moo.md/soloflow"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/soloflow.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.01083 |
| Opus 5 | $0.00007 | $0.00541 |
| Sonnet 5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
soloflow 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 7d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator of one goal that will run across several agents concurrently in Solo. Your job is to find the fastest route through it without compromising cost or quality.
Definitions
- you: elected lead, you have breadth and speed but lack facts and the user's ubiquitous language.
- brief: the goal in the record, minimal, read by every lane.
- scope: what an agent owns and may change freely.
- contract: the shared boundaries. What makes something a boundary? a lane may not change it alone.
- prompt: what a lane is spawned with.
- user: the goal owner, the work observer, their mental model comes out of their continuous journey.
Catch up, SILENTLY:
- Internalise the goal.
- Explore the project context.
- Pin the goal to the context.
- Extract the user mental model, if not already clear @references/mental-model.md.
- Group the files the goal touches into SCOPES
- Find what more than one scope touches: a file, a type, an ordering, a protocol, a function, etc.
- Are there any organizational changes to make delivering the goal concurrently more efficient (speed, cost, maintainability)?
- Yes? surface them to the user in few sentences. as a bullet list of before vs after.
- No? proceed to the next step.
Gate
- Warming an agent into a piece of work costs real money.
- A cold start is tens of thousands of tokens before anything happens.
- Reaching competence in a repo typically costs several dollars beyond it.
- IF one scope only? say so and STOP.
- A second lane must be worth its own warm-up and its own section in the record.
Mechanics
Specify the mechanics of each lane. Possible primitives, not limited to:
- Cost scales as context × turns, not context size only
- Concurrent spawns miss the prompt cache
- Each git worktree has a setup (installs, builds, tooling) cost you must satisfy.
Editis a compare-and-swap,Writeis a blind overwrite- Model tier is not free, plan wisely.
Record
- Pick a short
<slug>. - One Solo scratchpad,
nameandtagsboth<slug>with Sections:brief— the goal, as a lane needs to understand it. minimal.contract— what more than one scope touches. minimal.<slug>:<scope>— one per lane, headed — its scope, and which boundaries it owns.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 123 lines · 14 tokens per session scan A e0e16fbf881e
soloflow is a skill published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 21d ago), licensed MIT. It adds 14 tokens to every session and 1,083 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
session-recap
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
knowledge-bank-lookup
Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b]…
lark-openapi-explorer
A skill for finding and calling Lark APIs that are not already available through existing commands. An API is a defined way for software to request work from another service.
kb-ingest
Ingest external sources into the knowledge bank through interactive study or quick filing. Two modes — Quick (summarize → file) and Study (theme-by-theme deep dive with online research and personal notes → multi-layer KB output → optional blog/slack synthesis). Triggers on "ingest this", "study this article", "add to…
session-manager
Manage current Claude Code session metadata — set project, tags, and summary on session.md via Obsidian CLI. Use this skill whenever the user wants to tag, categorize, name, label, summarize, or organize the current session. Triggers on phrases like "tag this session", "this was about X", "mark this as", "session…
lark-workflow-standup-report
A Feishu (Lark) workflow that combines calendar events with unfinished tasks into a daily schedule summary. Feishu is a workplace collaboration app with calendar and task features.