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/refreshgit 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 | $0.00035 | $0.01094 |
| Opus 5 | $0.00017 | $0.00547 |
| Sonnet 5 | $0.00007 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
refresh 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:refresh
Atualização incremental da camada compilada.
Argumentos
$ARGUMENTS:
- vazio: atualiza só seções marcadas como stale
- nome de seção (e.g.,
01-topology): força refresh dessa seção --all: força refresh completo (equivalente a/fp:init --forcemas preserva backups)
Workflow
Passo 1 - Pre-flight
Verificar .first-plan/ existe. Se não, orientar a rodar /fp:init primeiro.
Passo 2 - Determinar escopo
- Ler
.first-plan/08-meta/cache.jsonpara identificar arquivos com hash diferente (modificados desde último init/refresh) - Ler
.first-plan/08-meta/coverage.mdseção "Stale" para arquivos marcados pelo hook - Mapear arquivos modificados → seções afetadas:
| Arquivo modificado | Seções afetadas |
|---|---|
| Manifesto (go.mod/package.json/etc) | 01-topology/stacks |
cmd/, entry points |
01-topology/architecture |
| Handlers / routers | 01-topology/boundaries |
| Dockerfile, .github/workflows | 01-topology/deployments |
| Qualquer código (>= 5 arquivos) | 01-topology/activity, 02-conventions/* |
| pkg/, lib/, utils/ | 03-reuse/* |
| Models, types | 04-domain/entities |
| Flows críticos (handlers de domínio) | 04-domain/flows |
| Tests | 02-conventions/testing, 05-risks/untested |
| Config files (lint, format) | 02-conventions/* |
| docs/, specs/ | 09-features/* |
Se $ARGUMENTS é nome de seção, force apenas essa.
Passo 3 - Refresh por seção
Para cada seção a atualizar:
01-topology/* (excluindo activity, ownership)
Spawnar discovery-analyst com escopo restrito (apenas reanalisar essa seção).
01-topology/activity, 01-topology/ownership
Inline - rodar comandos git novamente.
02-conventions/, 06-rationale/
Spawnar pattern-archeologist com categories=[<seção específica>].
03-reuse/*
Spawnar discovery-analyst com escopo reuse-only.
04-domain/*
Spawnar discovery-analyst com escopo domain-only.
05-risks/*
Spawnar discovery-analyst com escopo risks-only.
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 · 125 lines · 35 tokens per session scan A f7ab7ffcf031
refresh is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 1,094 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
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.
setup
Generate HOTL adapter files for your team's code assistants (Codex, Cline, Cursor, Copilot).