A command guide for reconciling project records so a pipeline mirror, task list, activity log, and follow-up items agree with their sources.

Use it to compare CRM records with pipeline notes, tasks with priorities, logs with Git history, and overdue marketing or customer-retention follow-ups.

It finds drift caused by multiple work sessions or outdated notes, while leaving decisions that require human judgment for the user.

reconcile — Command for Claude Code by etrebels: A command guide for reconciling project records so a…

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/etrebels/claude-code-growth-os/reconcile

Clone the repo

git clone --depth 1 https://github.com/etrebels/claude-code-growth-os

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/reconcile.svg)](https://agentmods.dev/commands/etrebels/claude-code-growth-os/reconcile)

Your own site

<a href="https://agentmods.dev/commands/etrebels/claude-code-growth-os/reconcile"><img src="https://agentmods.dev/badge/commands/etrebels/claude-code-growth-os/reconcile.svg" alt="Measured on agentmods" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 399 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00399
Opus 5	$0.00010	$0.00199
Sonnet 5	$0.00004	$0.00080
Haiku 4.5	$0.00002	$0.00040

Measured 5d ago against content hash 03595932e46f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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/commands/reconcile.md · 20 lines

What it actually says

Reconcile

Catch the drift that creeps in when more than one session writes to the same files — you at the keyboard plus a scheduled cloud routine. Read first, then fix; never guess at what changed.

Pipeline mirror vs CRM. If a CRM is connected, re-read it and compare to ops/pipeline.md per .claude/rules/crm-usage.md. On any conflict the CRM wins — rewrite the mirror. List what moved (deal · field · mirror → CRM).
Tasks vs priorities. Compare the one task list to ops/priorities.md (see .claude/rules/todo-single-source.md). Flag any Top-3 item that's done, gone, or missing from the source list. The list is the source; priorities.md only receives the derived view.
Log vs reality. Check the newest ops/daily-log.md date against today and against git log since it. If days were worked but never logged, name them.
Open loops. Surface any MARKETING-ACTION / RETENTION-RISK line in ops/feedback-log.md that's past its cadence with no resolution.
Fix the mechanical drift, surface the judgment calls. Rewrite the mirror and correct stale dates yourself; for anything that needs a decision, list it and ask — don't auto-resolve it.

Depth

quick: just the mirror-vs-CRM reconcile.
standard: all five checks.
deep: add a drift-pattern note — which file drifts most often, and which ritual would stop it at the source.

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.

5d ago First seen · 20 lines · 20 tokens per session scan A 03595932e46f

Subscribe to this mod's changes

reconcile is a command published in the GitHub repository etrebels/claude-code-growth-os (20 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 399 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 2026-08-30.

Project management agent-skills ai-agents claude-code devtools go-to-market marketing

reconcile

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Reconcile

Depth

What this file has done since we first saw it

Other commands, from other repositories

go-to-market

test-integration

doctor

triage-issues

export-clean

interactive-dev