first-plan-provenance-tracker

first-plan-provenance-tracker is a skill for Claude Code from vynazevedo/first-plan. It costs 64 tokens per session (2,185 once invoked), scanned A, original, MIT.

A tracking system for recording where project findings came from and how current they are. Each finding can include its source file and line, commit, confidence, expiry period and later replacement.

In plain words
What is it for?
Use it during project discovery and refreshes to document evidence for conventions, risks, facts, rules, features and reusable-code findings.
Why use it?
It helps prevent outdated or unsupported observations from being treated as facts. Developers can trace a planning note back to the code and see whether it may need refreshing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

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

Good fit Use it during project discovery and refreshes to document evidence for conventions, risks, facts, rules, features and reusable-code findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vynazevedo/first-plan/provenance-tracker
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.

Any agent
npx skills add vynazevedo/first-plan --skill provenance-tracker
Clone the repo
git clone --depth 1 https://github.com/vynazevedo/first-plan

Made for: Claude Code.

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 first-plan-provenance-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/vynazevedo/first-plan/provenance-tracker.svg)](https://agentmods.dev/skills/vynazevedo/first-plan/provenance-tracker)
Your own site
<a href="https://agentmods.dev/skills/vynazevedo/first-plan/provenance-tracker"><img src="https://agentmods.dev/badge/skills/vynazevedo/first-plan/provenance-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,185 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00064 $0.02185
Opus 5 $0.00032 $0.01092
Sonnet 5 $0.00013 $0.00437
Haiku 4.5 $0.00006 $0.00218

Measured 8d ago against content hash 240f90413226, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

first-plan-provenance-tracker 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 8d 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.

skills/provenance-tracker/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provenance & Freshness Tracker

Cada finding em .first-plan/ precisa de rastreabilidade completa - de onde veio, quando foi extraído, quão fresca é a info, quando expira, e o que substitui.

Por que existe

Sem provenance, fatos viram lendas. Esta skill garante que toda afirmação em .first-plan/ tem cadeia auditável até o código fonte. Isso elimina:

  • Context poisoning - fatos stale interpretados como atuais
  • Hallucinated facts - findings sem fonte verificável
  • Untrackable drift - quando um finding ficou errado e por quê
  • No-op refreshes - regerar tudo quando só uma coisa mudou

Schema de proveniência

Cada item em .first-plan/ (em qualquer arquivo) ganha campos no frontmatter ou inline (YAML/Markdown):

---
finding_id: F-<unique>            # identificador estavel (ex: F-go-errors-001)
type: pattern | fact | rule | risk | feature | reuse_item
section: <section path>           # ex: 02-conventions/errors

source:                           # de onde veio
  type: code | doc | git | mcp | inferred
  location: path:line             # arquivo:linha
  commit_sha: <SHA>               # commit em que foi observado
  extracted_from:                 # contexto adicional
    - <file_path>
    - <file_path>

extracted_at: 2026-05-04T22:00:00Z
extracted_by: discovery-analyst | pattern-archeologist | reconciliation-auditor | manual

confidence:
  initial: 0.95                   # confiança no momento da extração
  current: 0.92                   # após decay (calculado)
  signals_used:                   # o que sustenta o score
    - "10+ occurrences in current code"
    - "documented in CLAUDE.md"
    - "consistent across modules"

ttl:
  days: 30                        # validade default
  expires_at: 2026-06-03T22:00:00Z
  decay_curve: linear | step | none

lifecycle:
  status: active | superseded | invalidated | expired
  superseded_by: F-<id>           # se substituido por finding mais novo
  superseded_at: <timestamp>
  invalidated_reason: <text>      # se marcado invalido manualmente
---

Read the full file on GitHub · 282 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. 8d ago First seen · 282 lines · 64 tokens per session scan A 240f90413226

Subscribe to this mod's changes

first-plan-provenance-tracker is a skill published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 14d ago), licensed MIT. It adds 64 tokens to every session and 2,185 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

RecallMax

Enhances AI memory capabilities with long-context support.

Bilal140202/the-lord-of-the-skills · 13 tokens

agent-memory

Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…

OctavianTocan/agent-memory · 78 tokens

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

migrate

Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…

Bilal140202/the-lord-of-the-skills · 96 tokens

lookdev

When the user says "lookdev" (or asks to tune/dial/iterate on the look of something, OR to review/edit/annotate a blog post, doc, copy, or media), stand up a local interactive studio — live controls (sliders, pickers, drag handles) for visual params, OR direct inline editing + highlight + margin comments + media…

Bilal140202/the-lord-of-the-skills · 115 tokens

agentphone

Get your AI agent a real US/Canada phone number in one API call. Make voice calls, send and receive SMS, and hold actual conversations — all via API.

Bilal140202/the-lord-of-the-skills · 37 tokens