reconcile

reconcile is a command for Claude Code from punt-labs/punt-kit. It costs 10 tokens per session (1,482 once invoked), scanned A, original, MIT.

A command that checks a Punt Labs project against documented standards and applies context-sensitive fixes.

In plain words
What is it for?
Use it to inspect project type and configuration, run a deterministic audit, review standards, and reconcile workflows, CLAUDE.md, and pyproject.toml.
Why use it?
It combines automated checks with judgment about project files where simple mechanical checks may miss the intended setup.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the punt-dev plugin — 2 skills, 13 commands 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/punt-labs/punt-kit/reconcile
Clone the repo
git clone --depth 1 https://github.com/punt-labs/punt-kit

Made for: Claude Code.

Or install punt-dev, the plugin that ships this one along with the rest of its 2 skills, 13 commands.

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 reconcile

README.md
[![agentmods](https://agentmods.dev/badge/commands/punt-labs/punt-kit/reconcile.svg)](https://agentmods.dev/commands/punt-labs/punt-kit/reconcile)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/punt-kit/reconcile"><img src="https://agentmods.dev/badge/commands/punt-labs/punt-kit/reconcile.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,482 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 5.1 $0.00010 $0.01482
Opus 5 $0.00005 $0.00741
Sonnet 5 $0.00002 $0.00296
Haiku 4.5 $0.00001 $0.00148

Measured 5d ago against content hash 3bffcfb635fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reconcile 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.

plugin/commands/reconcile.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reconcile Project with Punt Labs Standards

Analyze a project against Punt Labs standards and surgically apply fixes. This command handles files that need contextual judgment — workflow customizations, CLAUDE.md quality, pyproject.toml drift — where a deterministic tool would be too blunt.

Input

Project path: $ARGUMENTS (defaults to . if empty)

Process

0. Detect Project

Read the project's pyproject.toml or package.json to determine:

  • Language (python, node, swift, or none)
  • Project type (application, library, plugin, docs)
  • Whether it has an MCP server (server.py or MCP-related deps)
  • Whether it has a CLI entry point ([project.scripts])

Also read the project's CLAUDE.md if it exists — it may document intentional overrides.

1. Run Deterministic Audit

Run the mechanical checks first:

punt audit <project-path>

Report the output to the user. The deterministic layer catches missing files, config gaps, and formatting issues. This command focuses on what punt audit cannot: contextual reconciliation.

2. Load Standards

Read the following files from the punt-kit standards directory. If punt-kit is a sibling directory (i.e., ../punt-kit/ relative to the project), read from the local filesystem. Otherwise, read from the punt-kit repo on GitHub.

  • standards/python.md — toolchain, quality gates, project layout
  • standards/github.md — CI workflows, markdownlint config, action SHA pins
  • standards/cli.md — required subcommands, init rules
  • standards/distribution.md — install paths, PyPI publishing
  • standards/plugins.md — plugin structure (if applicable)

3. Reconcile Workflow Files

For each workflow file in .github/workflows/:

  1. Read the project's current workflow
  2. Read the corresponding punt-kit template from src/punt_kit/templates/workflows/
  3. Identify:
    • Intentional customizations to PRESERVE: extra dependencies, cache config, system packages (e.g., ffmpeg), coverage integration, project-specific env vars, custom test commands, extra linting steps
    • Missing standard elements to ADD: new jobs, updated action versions, missing timeout settings, missing permissions declarations
    • Stale elements to UPDATE: outdated action SHA pins, deprecated syntax

Read the full file on GitHub · 158 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 · 158 lines · 10 tokens per session scan A 3bffcfb635fa

Subscribe to this mod's changes

reconcile is a command published in the GitHub repository punt-labs/punt-kit (1 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 1,482 once invoked, about $0.0001 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 2026-08-31.