agentmods.dev

first-plan-reconciliation

first-plan-reconciliation is a skill for Claude Code from vynazevedo/first-plan. It costs 70 tokens per session (1,595 once invoked), scanned A, original, MIT.

A method for comparing planned work—such as specifications, documentation, issues, and pull requests—with the code that actually exists. It labels each item as not started, partly done, complete, changed from the plan, or abandoned.

In plain words
What is it for?
Use it during project discovery or checks to trace requirements across repository documents, issue trackers, branches, pull requests, commits, code, and tests.
Why use it?
It prevents reimplementing features that already exist and exposes unfinished work or differences between the plan and the code.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

not rated 23repo 13d ago A scan 70 tokens original MIT

Good fit Use it during project discovery or checks to trace requirements across repository documents, issue trackers, branches, pull requests, commits, code, and tests.

Compare 6 skills from other repositories ↓
View source ↗ vynazevedo/first-plan
Install

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.

Claude Code
/plugin marketplace add vynazevedo/first-plan
Claude Code
/plugin install fp

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-reconciliation

README.md
[![agentmods](https://agentmods.dev/badge/skills/vynazevedo/first-plan/reconciliation.svg)](https://agentmods.dev/skills/vynazevedo/first-plan/reconciliation)
Your own site
<a href="https://agentmods.dev/skills/vynazevedo/first-plan/reconciliation"><img src="https://agentmods.dev/badge/skills/vynazevedo/first-plan/reconciliation.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,595 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.
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 $0.00070 $0.01595
Opus 5 $0.00035 $0.00797
Sonnet 5 $0.00014 $0.00319
Haiku 4.5 $0.00007 $0.00160

Measured 8d ago against content hash bc0be76c9074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

first-plan-reconciliation 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/reconciliation/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Code Reconciliation

Núcleo do diferencial do first-plan. Resolve "Claude reimplementa o que ja existe" e "Claude executa spec já feita".

Statuses possíveis

NOT_STARTED  -> intenção existe mas nenhum código relacionado
SPEC_ONLY    -> documentação completa, zero implementação
IN_PROGRESS  -> implementação parcial, branch ativa, ou TODOs visíveis
IMPLEMENTED  -> código completo, com testes
DRIFTED      -> código existe mas divergiu da spec
ABANDONED    -> branch obsoleta + implementação parcial

Coleta de intenções

Fontes ordenadas por prioridade:

  1. Documentação no repo:

    • docs/, specs/, requirements/, rfcs/
    • Arquivos *.md com headings tipo "## Feature:", "## Requisito:", "## RFC"
    • README sections com "Roadmap", "Planned features", "TODO"
    • CHANGELOG (entradas pré-release ou "Unreleased")
    • ADRs (Architecture Decision Records)

  2. Issue trackers via MCP:

    • JIRA via mcp__jira-mm__* (issues recentes do projeto, status != Done)
    • GitHub Issues via mcp__github-work__list_issues
    • Linear, Asana se MCPs disponíveis

  3. Git artifacts:

    • Branches com nome feat/, feature/, wip/
    • PR descriptions / templates
    • Commits com tag [FEAT] / feat:

  4. Comentários no código:

    • // TODO: implement <X>
    • // FIXME: this is partial
    • // PLANNED: <feature>

Algoritmo de classificação

Para cada intenção coletada (chamada de "feature candidate"):

Passo 1 - Extrair termos-chave

Da descrição/título da intenção, extrair:

  • Substantivos (entidades, ações)
  • Identificadores prováveis (URLs, endpoints, nomes de classes)
  • Stack-specific keywords (e.g., "endpoint POST /users" -> grep por POST /users)

Passo 2 - Buscar evidência no código

Para cada termo-chave:

  • Grep símbolos: nomes de função, classe, tipo, route
  • Grep arquivos: nomes de arquivo similar
  • AST scan se a stack permite: identificar handlers HTTP que respondem ao endpoint da spec
  • Grep testes: arquivos de teste mencionando o termo

Read the full file on GitHub · 166 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 · 166 lines · 70 tokens per session scan A bc0be76c9074

Subscribe to this mod's changes

first-plan-reconciliation is a skill published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 13d ago), licensed MIT. It adds 70 tokens to every session and 1,595 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.

Claude CodeCode reviewPlanningai-codingaiderclinecodexcontext
Related

Other skills, from other repositories

should-flag-change

Decide whether a given code change should be placed behind a LaunchDarkly feature flag. Use when a developer asks whether a change should be behind a flag, when reviewing a diff or pull request, or when running in CI on a PR. Reads the diff and surrounding code, then emits a structured advisory recommendation.…

Bilal140202/the-lord-of-the-skills · 78 tokens

arch-check

An architecture and implementation review tool that examines how a codebase is modeled, divided into responsibilities, organized into modules, and connected by dependencies. It also checks for issues such as circular dependencies, over-design, and violations of common design principles.

AgentsMesh/AgentsMesh · 212 tokens

greploop

Iteratively improves a PR until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully optimize a PR against Greptile's code review standards.

Bilal140202/the-lord-of-the-skills · 68 tokens

agy-review

Adversarially review anything - a plan, design, code change, piece of writing, decision, argument, config, or idea - with the agy (Antigravity) CLI. A fast second opinion from an independent model that pokes holes in whatever you give it - questionable assumptions, flaws, risks, gaps, failure modes, and a…

Bilal140202/the-lord-of-the-skills · 152 tokens

pr-reviewing

Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.

yimwoo/hotl-plugin · 38 tokens

code-review

Use after completing implementation steps and before merging — reviews against plan and HOTL contracts.

yimwoo/hotl-plugin · 20 tokens