Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add felvieira/claude-skills-fv/plugin install dev-team-kit-fvWrote 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/felvieira/claude-skills-fv/savings)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/savings"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/savings/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/savings"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/savings.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01126 |
| Opus 5 | $0.00019 | $0.00563 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
savings 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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/savings — Quanto o kit te salvou
Objetivo: mostrar de forma honesta e auditável quanto o dev-team-kit-fv contribuiu durante seu uso — em tokens economizados, dinheiro, bugs prevenidos e tempo equivalente de dev.
Não é métrica de marketing. As heurísticas estão declaradas em policies/savings-metrics.md para você auditar.
Como invocar
/savings # all-time, projeto atual
/savings --since 24h # últimas 24 horas
/savings --since 7d # últimos 7 dias
/savings --since 30d # últimos 30 dias
O que mostra
| Seção | Conteúdo |
|---|---|
| 💰 Bottom line | Tokens estimados, USD, bugs prevenidos, dev hours equivalentes, valor combinado |
| 🛡 Agent Dispatch Validator | Quantas vezes bloqueou skill-as-subagent (evitando InputValidationError), top offenders |
| 🎯 Pre-Execution Gate | Distribuição de decisões: concrete bypass / open discussion / enrich / guided enrich / force |
| 📂 Tool Usage | Reads/searches/writes totais, bytes lidos, hot files (candidatos a learned-skill) |
| ⚙ Tool Call Activity | Total calls, error rate, bytes returned, avg bytes/call (eficiência), span da atividade |
| 🧠 Intent Classifier | Total classificações, LLM vs regex, distribuição por categoria |
| 🧭 Routing Feedback | Composições aceitas, alteradas ou rejeitadas; sinal para calibrar triggers sem inflar skills |
Execute
Rode o engine de relatório e mostre o output diretamente:
node "${CLAUDE_PLUGIN_ROOT}/scripts/savings-report.mjs" $ARGUMENTS
Após o output, interprete brevemente os 3 maiores insights:
- O que mais economizou (qual hook foi MVP)
- O que pode ser melhorado (hot files repetidos → criar learned-skill? Hooks ignorados → calibrar?)
- Sugestão acionável para próxima semana
Fontes de dados
| Arquivo | Origem | O que tem |
|---|---|---|
.auto/events.jsonl |
session-event-logger (PostToolUse) |
toda tool call: ts, tool, args, status, bytes_out |
.bot/.tool-usage.json |
pre-tool-enforcer (PreToolUse) |
reads/searches/writes counters, repeated signals, hot files |
.bot/agent-dispatch-errors.jsonl |
agent-dispatch-validator (PreToolUse, v2.2.1+) |
blocked Agent dispatches com skill name como subagent_type |
.bot/pre-execution-gate.jsonl |
pre-execution-gate (UserPromptSubmit, v2.4.0+) |
decisões do gate: concrete_bypass / open_discussion_bypass / enrich / guided_enrich / force_bypass / pass_through |
.swarm/classifier.jsonl |
intent-classifier (UserPromptSubmit) |
classificações de intent: categoria, command sugerido, LLM vs regex |
.bot/route-feedback.jsonl |
route-feedback.mjs |
decisões explícitas accepted/overridden/rejected e plugins selecionados |
.bot/conflict-decisions.jsonl |
policies/trade-off-resolution.md via scripts/log-conflict-decision.mjs (v2.7.1+) |
resoluções de conflito: policies envolvidas, resolution type, outcome |
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.
- 12d ago First seen · 79 lines · 39 tokens per session scan A 406ad2902d4e
savings is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,126 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.