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/vynazevedo/first-plan/in-flightgit clone --depth 1 https://github.com/vynazevedo/first-planWrote 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/vynazevedo/first-plan/in-flight)<a href="https://agentmods.dev/commands/vynazevedo/first-plan/in-flight"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/in-flight.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 | $0.00028 | $0.00628 |
| Opus 5 | $0.00014 | $0.00314 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
in-flight 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:in-flight
Branches e PRs em movimento.
Argumentos
$ARGUMENTS:
- vazio: mostra trabalho em flight (default)
--all: inclui branches stale e PRs draft--mine: filtra para branches/PRs do usuário atual
Workflow
Passo 1 - Pre-flight
Verificar git repo. Verificar .first-plan/07-state/in-flight.md existe.
Passo 2 - Render
Ler 07-state/in-flight.md (snapshot mais recente). Se stale (> 24h), reroda inline a coleta.
Passo 3 - Apresentar
Trabalho em flight (atualizado em <timestamp>)
Branches ativas (commit < 7 dias):
- feat/2fa João Silva 2 dias +127/-23 vs main PR #42 aberto
- feat/audit-log Maria Lima 1 dia +89/-12 vs main sem PR
- fix/payment-bug Pedro Souza 3h +5/-2 vs main PR #45 aberto
Branches stale (7-30 dias):
- feat/csv-export João Silva 12 dias +45/-3 vs main PR #38 (sem revisão há 8 dias)
Pull Requests abertos (<count>):
#42 [feat/2fa] Two-Factor Authentication João ⏳ aguardando review
#45 [fix/payment] Fix retry on payment timeout Pedro ✓ aprovado, aguarda merge
#38 [feat/csv-export] Add CSV export to /orders João ⚠ stale, sem update há 8 dias
WIP detectado:
- branch: wip/refactor-handlers (Maria, 5 dias)
Conflitos potenciais:
(se algum branch toca arquivos críticos do projeto, listar)
Passo 4 - Modes
--all: inclui também branches abandoned (>30 dias), PRs draft.
--mine: filtra git config user.email e mostra apenas matches.
Passo 5 - Sem MCP/gh
Se MCP github-work não disponível e gh CLI não instalado:
Trabalho em flight (limitado a dados locais - PRs externos não consultados)
Branches locais e remotas:
<lista via git for-each-ref>
Para PRs, instalar gh CLI ou habilitar MCP github-work.
Atualização
Se in-flight.md está stale (> 24h):
- Avisar
- Oferecer rerun inline
07-state/in-flight.md está com 2 dias de idade.
Rodando refresh inline...
[output]
Para snapshot persistido: /fp:refresh 07-state
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.
- 5d ago First seen · 86 lines · 28 tokens per session scan A b2a1f367a840
in-flight is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 628 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 commands, from other repositories
selfreview
Self code review before a release — four narrow reviewers over the change (or the whole repo), findings ranked, nothing edited.
gate
Run the full local gate (fmt, lint, test, build, docs, and fuzz when a parser changed) and report only what failed.
release
Prepare the next release per RELEASING.md — gate, price table, surface audit, changelog — and stop at the tag command.
matcha:review
🍵 Review gate — risk-based code review (L0-L3). Nothing ships until this passes.
matcha:audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems.
matcha:why
🍵 Intent Discovery — problem, goals, success criteria, What → Why → How before touching code.