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/quickgit clone --depth 1 https://github.com/vynazevedo/first-planWhat 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 | $0.00045 | $0.01461 |
| Opus 5 | $0.00023 | $0.00731 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
quick scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:quick
Resumo executivo do projeto em ~30s. Gera .first-plan/quick/00-glance.md com 1 página de contexto suficiente para o Claude começar a ajudar imediatamente, sem rodar o init completo (3-8 min).
Quando usar
- Primeira vez no projeto - quer ver valor em <1 minuto antes de investir 5 min no init
- Sessão nova num projeto que ja tem
.first-plan/- quer recap rapido sem re-rodar tudo - Demo/screenshot - mostra capacidade do plugin sem espera
- CI/CD ou ambiente restrito - quer contexto rapido sem indices pesados
Para analise completa (reuse index, reconciliation, co-change graph, provenance), rode /fp:init depois.
Workflow
Passo 1 - Engine check
ENGINE=$(which first-plan-engine 2>/dev/null || echo "${CLAUDE_PLUGIN_ROOT}/engine/bin/first-plan-engine")
if [ ! -x "$ENGINE" ]; then
echo "Engine nao encontrado. /fp:quick requer first-plan-engine v0.7.0+."
echo "Instale: cargo install --git https://github.com/vynazevedo/first-plan --path engine/crates/cli"
echo "Ou baixe binario: https://github.com/vynazevedo/first-plan/releases/latest"
exit 0
fi
Passo 2 - Rodar glance e salvar arquivo
mkdir -p .first-plan/quick
"$ENGINE" quick --root "$PWD" --output .first-plan/quick/00-glance.md --json > /tmp/fp-quick.json
Tempo tipico: 1-5s (rapido em projetos pequenos, ate 30-40s em monorepos grandes).
Passo 3 - Ler o JSON pra apresentar resumo
cat /tmp/fp-quick.json
JSON estrutura:
{
"elapsed_ms": 1289,
"root": "/path/to/project",
"stacks": [{"language": "Rust", "manifest": "engine/Cargo.toml"}],
"entry_points": ["engine/crates/cli/src/main.rs"],
"top_symbols": [{"name": "Args", "kind": "struct", "file": "...", "line": 17}],
"git_activity": {
"recent_commits": ["..."],
"hot_files": [{"path": "...", "change_count": 12}],
"active_authors": [{"name": "...", "commit_count": 47}]
},
"conventions": {
"naming": "snake_case predominante (45 de 50 arquivos)",
"test_frameworks": ["Rust #[cfg(test)] mod tests inline"]
},
"commands": ["cargo build --release (in engine)", "cargo test --workspace (in engine)"]
}
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 · 156 lines · 45 tokens per session scan A 571326b9f58a
quick is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 1,461 once invoked, about $0.0002 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
check-contributors
Checks who's working on the project and optionally converts to a multi-person project with team state management.
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
polyphony-status
Display the current state of all Polyphony tasks and running containers.
set-tracker
Set the issue tracker for the current project.
projects
List registered projects and instinct counts.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…