provenance

provenance is a command for coding agents from vynazevedo/first-plan. It costs 43 tokens per session (1,005 once invoked), scanned A, original, MIT.

A command for tracing a finding back to its source, such as the code, commit, and files where it was identified. It also reports its current confidence, status, age, and whether it has been checked again.

In plain words
What is it for?
Use it to audit one finding or a group of findings by ID or pattern, inspect their stored details, and review when they were extracted and last revalidated.
Why use it?
It makes the origin and freshness of a reported claim visible, so developers can judge whether it is still trustworthy.

Command

Part of the fp plugin — 19 skills, 19 commands, 4 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/vynazevedo/first-plan/provenance
Clone the repo
git clone --depth 1 https://github.com/vynazevedo/first-plan

Or install fp, the plugin that ships this one along with the rest of its 19 skills, 19 commands, 4 agents, 1 hook.

Wrote 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.

agentmods badge for provenance

README.md
[![agentmods](https://agentmods.dev/badge/commands/vynazevedo/first-plan/provenance.svg)](https://agentmods.dev/commands/vynazevedo/first-plan/provenance)
Your own site
<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>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 440ce93788a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commands/provenance.md · 143 lines

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

Read the full file on GitHub · 143 lines

Changes

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.

  1. 5d ago First seen · 143 lines · 43 tokens per session scan A 440ce93788a4

Subscribe to this mod's changes

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.