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 commands/ma-nucho-pro/wingman/savegit clone --depth 1 https://github.com/ma-nucho-pro/WingmanWrote 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/ma-nucho-pro/wingman/save)<a href="https://agentmods.dev/commands/ma-nucho-pro/wingman/save"><img src="https://agentmods.dev/badge/commands/ma-nucho-pro/wingman/save.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 | $0.00012 | $0.00202 |
| Opus 5 | $0.00006 | $0.00101 |
| Sonnet 5 | $0.00002 | $0.00040 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
save 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 4d 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.
What it actually says
Write a handoff for whoever picks this project up next — a different AI tool, or you on another computer. Use exactly these sections:
## Goal
## Current state (branch, last commit, what passes, what fails)
## Decisions made (and why)
## Dead ends (tried, did not work, do not retry)
## Files touched
## Next concrete step (specific enough to start immediately)
Write state, not transcript: 200-400 words. The code is already on disk; what is lost between tools is the reasoning, not the diff. Never include API keys, tokens or passwords.
Then save it by piping that Markdown to:
npx -y wingman-ai@latest save --agent claude-code --title "<short summary>" --stdin
Confirm to the user what was saved and whether it synced.
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.
- 4d ago First seen · 27 lines · 12 tokens per session scan A 09803bc51e7f
save is a command published in the GitHub repository ma-nucho-pro/Wingman (4 stars, last pushed 27d ago), licensed MIT. It adds 12 tokens to every session and 202 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 2026-08-31.
Other commands, from other repositories
deja
Search this machine's past AI coding sessions (deja-vu).
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
goal
Complete reference for all goal-related commands — definition, refinement, execution, review, codification, and management.
decisions
Complete reference for managing architectural decision records (ADRs).
guidelines
Complete reference for managing execution guidelines — testing, coding style, process, and more.
work
Complete reference for work refine, work review, work pause, and work resume commands.