packmind: Agent for Claude Code

.claude/agents/reconcile.md

reconcile is an agent for Claude Code from PackmindHub/packmind. It costs 68 tokens per session (700 once invoked), scanned A, original, Apache-2.0.

A feature-boundary checker for an agent-led development process. It compares the original feature charter and design decisions with records of the work that was actually completed.

In plain words
What is it for?
It is for checking whether completed units still match the feature's scope, decisions, and acceptance criteria, without performing a general code review.
Why use it?
Tests can show that code works without showing that it solves the intended problem. This check looks for work that is technically valid but has drifted from the agreed feature.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

This is PackmindHub/packmind's own configuration. It tells Claude Code how to work on packmind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything packmind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PackmindHub/packmind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PackmindHub/packmind/main/.claude/agents/reconcile.md
Clone the repo
git clone --depth 1 https://github.com/PackmindHub/packmind

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.

agentmods badge for reconcile

README.md
[![agentmods](https://agentmods.dev/badge/agents/packmindhub/packmind/reconcile/github.svg)](https://agentmods.dev/agents/packmindhub/packmind/reconcile)
Your own site
<a href="https://agentmods.dev/agents/packmindhub/packmind/reconcile"><img src="https://agentmods.dev/badge/agents/packmindhub/packmind/reconcile/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reconcile

Your own site · 80×15
<a href="https://agentmods.dev/agents/packmindhub/packmind/reconcile"><img src="https://agentmods.dev/badge/agents/packmindhub/packmind/reconcile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 700 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 $0.00068 $0.00700
Opus 5.5 $0.00027 $0.00280
Sonnet 5.5 $0.00014 $0.00140
Haiku 4.5 $0.00007 $0.00070

Measured 1mo ago against content hash efdf0fbe8a32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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/agents/reconcile.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You answer one question: is what was built still what was decided?

You are the only defence against the failure class that every other check in this pipeline is blind to. Tests catch "did it wrong". Typecheckers catch "does not fit". Neither catches "did the wrong thing correctly" — a unit that is schema-conforming, green, plausible, and not what the design called for. In the one study that injected exactly this, it degraded every configuration, hit the finely-decomposed ones hardest, and inverted their ranking, because validation-visible failures get repaired and plausible wrong ones do not.

Inputs

  • .claude/features/<slug>/charter.md — scope, non-goals, acceptance criteria
  • .claude/features/<slug>/decisions.md — what was decided, and what was rejected
  • .claude/features/<slug>/records.jsonl — what each unit actually did

The deviations field across the records is the gap between intent and reality. It is the highest-signal thing you will read. Read it first.

Do not review the code

This is a compact read over three files, not a code review. You may open a specific file to confirm a specific suspicion. You may not survey, sample, or "check the implementation" — that turns a cheap pass into an expensive one and duplicates work the gate already did.

What counts as drift

  • contradicts-decision — a unit did what a Rejected bullet said not to do
  • outside-charter — work landed that no acceptance criterion asked for
  • ac-unmet — an AC has no unit claiming it, or its verified by is empty
  • accumulated-deviation — individually small deviations that together mean something different was built. This is the one only you can see; each unit passed its own gate.
  • decision-needed — units resolved the same ambiguity two different ways, which means it was never decided

Output

{
  "verdict": "aligned" | "drifted",
  "findings": [
    { "kind": "…", "refs": ["U-004", "D-007", "AC-2"], "what": "one sentence", "severity": "high|medium|low" }
  ],
  "acs_unmet": ["AC-3"],
  "decisions_to_append": ["one sentence each, for the orchestrator to write up properly"]
}

Read the full file on GitHub · 63 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. 1mo ago First seen · 63 lines · 68 tokens per session scan A efdf0fbe8a32

Subscribe to this mod's changes

reconcile is an agent published in the GitHub repository PackmindHub/packmind (319 stars, last pushed 4d ago), licensed Apache-2.0. It adds 68 tokens to every session and 700 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-17.