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/provenancegit 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/provenance)<a href="https://agentmods.dev/commands/vynazevedo/first-plan/provenance"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/provenance.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01005 |
| Opus 5 | $0.00022 | $0.00502 |
| Sonnet 5 | $0.00009 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
provenance 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 5d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:provenance
Auditoria de proveniência de findings.
Argumentos
$ARGUMENTS - finding ID (ex: F-go-errors-001) ou padrão de busca (ex: F-go-*).
Workflow
Passo 1 - Buscar finding
Grep por finding_id: <ID> em todos arquivos .first-plan/:
grep -rln "finding_id: $ARGUMENTS" .first-plan/
Se não encontrar match exato, tentar como prefix.
Passo 2 - Extrair frontmatter completo
Ler arquivo e parsear o block YAML do finding.
Passo 3 - Calcular confidence current
Aplicar decay rule da skill provenance-tracker:
age_days = (now - extracted_at).days
multiplier = decay_curve_lookup(age_days)
current = initial * multiplier
Passo 4 - Apresentar
=== Provenance Report ===
Finding: F-go-errors-001
Type: pattern
Section: 02-conventions/errors
Status: active
Source:
Type: code
Location: internal/service/user.go:47
Commit SHA: abc1234 (HEAD: def5678 - 12 commits ahead)
Extracted from:
- internal/service/user.go
- internal/service/order.go
- internal/service/payment.go (3 files total)
Timeline:
Extracted at: 2026-04-15T10:00:00Z (20 days ago)
Last revalidated: never
TTL expires at: 2026-05-15T10:00:00Z (10 days remaining)
Confidence:
Initial: 0.95
Current: 0.85 (decayed - 30-90 days range)
Signals used:
- "12 occurrences"
- "consistent across all services"
Lifecycle:
Status: active
Superseded by: none
Supersedes: none
Invalidated: no
Health: HEALTHY
- Above threshold (0.85 > 0.7)
- Within TTL (10 days left)
- Source still exists in codebase
Recommendations:
- Acceptable to use as basis for new code
- Consider /fp:refresh 02-conventions/errors before deadline
Passo 5 - Casos especiais
Finding superseded
Status: SUPERSEDED
Superseded by: F-go-errors-007 at 2026-05-01
Reason: New pattern emerged using errors.Join (Go 1.20+)
DO NOT USE THIS FINDING. Reference F-go-errors-007 instead.
View it: /fp:provenance F-go-errors-007
Finding invalidated
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.
- 5d ago First seen · 143 lines · 43 tokens per session scan A 440ce93788a4
provenance is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 1,005 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
selfreview
Self code review before a release — four narrow reviewers over the change (or the whole repo), findings ranked, nothing edited.
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.