reconcile

reconcile is a skill for Claude Code, Codex from asteasolutions/ai-toolkit. It costs 85 tokens per session (642 once invoked), scanned A, original, MIT.

A closing report that compares a planned change with what was actually built.

In plain words
What is it for?
Use it after following a plan or specification, especially when reviewing whether the finished work matches the original intent.
Why use it?
It highlights deviations, decisions made during implementation, unmet goals, and documentation that may need updating.

Skill for Claude CodeCodex

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 skills/asteasolutions/ai-toolkit/reconcile
Any agent
npx skills add asteasolutions/ai-toolkit --skill reconcile
Clone the repo
git clone --depth 1 https://github.com/asteasolutions/ai-toolkit

Made for: Claude Code, Codex.

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/skills/asteasolutions/ai-toolkit/reconcile.svg)](https://agentmods.dev/skills/asteasolutions/ai-toolkit/reconcile)
Your own site
<a href="https://agentmods.dev/skills/asteasolutions/ai-toolkit/reconcile"><img src="https://agentmods.dev/badge/skills/asteasolutions/ai-toolkit/reconcile.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 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 $0.00085 $0.00642
Opus 5 $0.00043 $0.00321
Sonnet 5 $0.00017 $0.00128
Haiku 4.5 $0.00009 $0.00064

Measured 5d ago against content hash d19889e9ad90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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.

.claude/skills/reconcile/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reconcile

Close the loop by reporting the delta — the gap between what was planned and what was built. Nothing else.

A diff already shows what changed. Re-narrating it wastes tokens and, worse, breeds false confidence — a self-report of the diff can flatter or mislead. The developer reads the diff for the what; they read you for what the diff hides: the forks taken, the things not done, the calls made in the dark. Surface only those, so the developer re-examines the delta instead of re-deriving the whole change.

The ledger

Record exactly these, and stop:

  • Deviations — where execution left the plan, and why.
  • Decisions — judgment calls the plan did not pin down: a name, an edge case skipped, an error-handling choice. The most important line, and the easiest to under-report because each call felt obvious when you made it. Re-scan the diff for every choice the plan left open; list them, don't assume none. They are decisions the developer owns but never explicitly made.
  • Verify-against-intent — does the result satisfy the intent's success criteria? Name the check; do not assert success without one.
  • Doc impact — default none. Escalate only when a durable decision changed the domain model and domain knowledge docs already exist. When you escalate, propose the concrete edit and, once the developer approves, make it — never merely note that a doc "should" change. Discover the repo's existing form (glossary, decision log, ADR tree, …); do not invent a layout or create new domain-doc trees. This promotes the durable part of the work out of disposable scratch into the committed, shared layer.

If execution matched the plan with no unplanned decisions, the whole reconcile is one line: "Executed as planned, no deviations." Resist padding it.

Then update the program counter

Reconcile is also where the work tree advances:

  • Stamp this node's one-line outcome into the parent map (<goal-slug>/_map.md), so the map carries the whole goal at a glance without the detail. (A single, undecomposed goal has no map — its own Reconcile section is the record.)
  • If a deviation or decision invalidates a downstream task, say so plainly and flag the affected tasks for re-planning — one surprise must not silently rot the rest of the plan. Reopen only the affected tasks, not the whole decomposition.

Read the full file on GitHub · 31 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 31 lines · 85 tokens per session scan A d19889e9ad90

Subscribe to this mod's changes

reconcile is a skill published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 642 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens