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.
git 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/features)<a href="https://agentmods.dev/commands/vynazevedo/first-plan/features"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/features/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/vynazevedo/first-plan/features"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/features.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 | $0.00029 | $0.00642 |
| Opus 5.5 | $0.00012 | $0.00257 |
| Sonnet 5.5 | $0.00006 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
features 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:features
Matriz de Spec-Code Reconciliation.
Argumentos
$ARGUMENTS:
- vazio: tabela completa
status:<X>: filtrar por status específicophantom: apenas phantom featuresdrifted: apenas drift detectado
Workflow
Passo 1 - Pre-flight
Verificar .first-plan/09-features/INDEX.md existe.
Passo 2 - Carregar matriz
Ler INDEX.md + frontmatter + tabela.
Passo 3 - Aplicar filtro
Se filtro aplicado, manter apenas linhas que casam.
Passo 4 - Apresentar
Default:
Matriz de features (<total>)
IMPLEMENTED (<a>):
F1 User Authentication via JWT conf 0.91 evidência: internal/auth/jwt.go
F3 Password Reset Flow conf 0.85 evidência: internal/auth/reset.go
...
IN_PROGRESS (<b>):
F5 Two-Factor Authentication conf 0.78 branch: feat/2fa, PR #42
...
SPEC_ONLY (<c>):
F7 CSV Export conf 0.92 fonte: JIRA-456
...
NOT_STARTED (<d>):
F9 Audit Log Replay conf 0.70 fonte: docs/audit.md
...
DRIFTED (<e>) ⚠
F12 Email Validation conf 0.82 drift: regex permissiva vs spec estrita
...
ABANDONED (<f>):
F15 Old Notification Center conf 0.65 branch obsoleta há 4 meses
...
Phantom features ⚠ (<g>):
F8 Pagination on /users implementada mas JIRA-234 ainda Open
Detalhes individuais: .first-plan/09-features/<slug>.md
Filtrado:
Features com status=IMPLEMENTED (<count>)
F1 User Authentication via JWT conf 0.91
fonte: docs/auth.md
evidência: internal/auth/jwt.go:1-150 + tests
detalhes: .first-plan/09-features/user-authentication-jwt.md
F3 Password Reset Flow conf 0.85
...
Passo 5 - Alertas
Sempre destacar:
- Phantom features (alerta forte)
- DRIFTED (alerta médio)
- IN_PROGRESS sem update há > 30 dias (sinal de abandonment iminente)
Cuidados
- Se INDEX.md está stale, recomendar
/fp:refresh 09-featuresantes de confiar plenamente.
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.
- 1mo ago First seen · 95 lines · 29 tokens per session scan A 53a9734836ec
features is a command published in the GitHub repository vynazevedo/first-plan (24 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 642 once invoked, about $0.0001 per session on Opus 5.5. 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
matcha:why
🍵 Intent Discovery — problem, goals, success criteria, What → Why → How before touching code.
matcha:markers
🍵 Scan for // matcha: markers in the codebase and group by severity.
matcha:status
🍵 Master session health dashboard — intensity, git diff stats, test status, and marker ledger.
matcha:off
🍵 Disable matcha — completely silent, zero token overhead.
matcha:intensity
🍵 Set matcha intensity level: observe, enforce, or audit.
matcha:toggle
🍵 Toggle matcha governance on/off (instant switch).