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/rollbackgit 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 | $0.00037 | $0.01124 |
| Opus 5 | $0.00018 | $0.00562 |
| Sonnet 5 | $0.00007 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade C, and why
rollback scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .first-plan How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:rollback
Reverte mudanças do último execute (ou snapshot específico).
Argumentos
$ARGUMENTS:
- vazio: rollback do último execute
--dry-run: mostra o que seria revertido sem aplicar--snapshot <id>: rollback para snapshot específico (ID do timestamp)
Workflow
Passo 1 - Pre-flight
Verificar .first-plan/cache/snapshots/ existe e tem ao menos 1 snapshot.
Passo 2 - Identificar snapshot alvo
ls -t .first-plan/cache/snapshots/ | head -5
Output exemplo:
2026-05-04T22-35-01-pre-execute-csv-export
2026-05-04T18-12-44-pre-execute-auth-jwt
2026-05-03T15-22-08-pre-execute-rate-limit
Default: snapshot mais recente. Se --snapshot <id>: usar esse.
Passo 3 - Mostrar diff
=== Rollback preview ===
Snapshot alvo: 2026-05-04T22-35-01-pre-execute-csv-export
Idade: 23 minutos
Mudanças que serão revertidas em .first-plan/:
- 09-features/csv-export.md (criado pelo execute)
- 07-state/STATE.md (phase voltará para awaiting_approval)
- 07-state/reports/csv-export.md (será removido)
- 07-state/reports/csv-export-verification.md (será removido)
Mudanças no working tree (NÃO revertidas automaticamente):
- internal/handler/export.go (modified)
- internal/service/csv_writer.go (created)
- internal/service/csv_writer_test.go (created)
Para reverter working tree manualmente:
git checkout HEAD -- internal/handler/export.go
rm internal/service/csv_writer.go internal/service/csv_writer_test.go
OU se já commitou:
git revert <commit-sha>
Continuar com rollback do .first-plan/? [s/N]
Passo 4 - Aplicar (se confirmado)
# Backup do estado atual antes de rollback (snapshot do snapshot)
cp -r .first-plan .first-plan.before-rollback-$(date +%s)
# Restaurar snapshot
rm -rf .first-plan
cp -r .first-plan/cache/snapshots/<snapshot-id>/snapshot/.first-plan .first-plan
Atualizar STATE.md:
phase: awaiting_approval # ou phase pré-execute do snapshot
last_rollback_at: <ISO>
rolled_back_to: <snapshot-id>
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 · 147 lines · 37 tokens per session scan C d41c89306935
rollback is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 1,124 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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).