MarkdownLLM: Command for Claude Code

.claude/commands/retrospective.md

retrospective is a command for Claude Code from JanoshMoshiri/MarkdownLLM. It costs 32 tokens per session (752 once invoked), scanned A, original, MIT.

A command for periodically reviewing a project's knowledge, rules, and recorded contradictions. A retrospective is a review of what happened and what should change.

In plain words
What is it for?
It is for writing a review record, scanning linked information for contradictions, checking whether the project's data fields still fit together, and deciding which skills to update or retire.
Why use it?
It helps find conflicting information, inconsistent field names, and outdated skills before they cause further problems.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is JanoshMoshiri/MarkdownLLM's own configuration. It tells Claude Code how to work on MarkdownLLM 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 MarkdownLLM configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JanoshMoshiri/MarkdownLLM. 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/JanoshMoshiri/MarkdownLLM/main/.claude/commands/retrospective.md
Clone the repo
git clone --depth 1 https://github.com/JanoshMoshiri/MarkdownLLM

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 retrospective

README.md
[![agentmods](https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/retrospective/github.svg)](https://agentmods.dev/commands/janoshmoshiri/markdownllm/retrospective)
Your own site
<a href="https://agentmods.dev/commands/janoshmoshiri/markdownllm/retrospective"><img src="https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/retrospective/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 retrospective

Your own site · 80×15
<a href="https://agentmods.dev/commands/janoshmoshiri/markdownllm/retrospective"><img src="https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 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 $0.00032 $0.00752
Opus 5 $0.00016 $0.00376
Sonnet 5 $0.00006 $0.00150
Haiku 4.5 $0.00003 $0.00075

Measured today against content hash a0ea33d80371, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

retrospective 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 today.

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/retrospective.md · 49 lines

What it actually says

Write a type: retrospective thing for this domain (periodic quality reflection; see retrospective.md), then run the reflexive scans that spec binds to this ritual. retrospective.mdReflexive Scans At Retrospective owns each scan's definition and its number; this file is the invocation, and until 2026-09-08 it fired three of the seven — the net beneath the net was never wired to the hand that casts it.

  1. detect-conflicts (scan mode; spec scan 1) — sweep every linked_things edge across the domain for contradictions; templates/prompts/detect-conflicts.md.
  2. Triage every open conflict (spec: What A Retrospective Produces, item 3) — walk things/conflicts/ at status: open, the whole set and not only what the floor aged, and force a disposition on each: rule (superseded / both-valid / dismissed → status: resolved), link it from the work that will resolve it, or hold it with disposition: keep-active + a disposition_reason naming what would resolve it. Creation runs at three cadences; this and the end-session brake are the two that read.
  3. review-schema-coherence (spec scan 2) — audit the emergent frontmatter vocabulary for fields that have drifted apart in name but converged in meaning; templates/prompts/review-schema-coherence.md.
  4. Index rebuild (spec scan 3) — python tools/mdllm.py index . rebuild. The floor refuses a drifted index at every commit, so this resets the provenance anchors to the period's end; content parity never depended on it.
  5. Change-driven reconciliation (spec scan 4) — for every change the period landed without a declared inflection, run the backward pass (change-reconciliation.md → Retrospective Reconciliation): freeze a baseline, reconstruct the delta from git log over the period, assimilate each changed thing's affected set (mdllm touchpoints), walk it, and seal contradictions as type: conflict things. This is the only pass that catches an inflection nobody declared — including every change an unattended agent commits.
  6. Insight triage and consolidation (spec scan 5) — act on the insight orphan findings (validate), then cluster active insights sharing two or more linked_things targets as merge candidates and judge each cluster.
  7. Conditions-met pass (spec scan 6) — re-read every disposition_reason on the kept insights and the held conflicts, and rule on each condition that has since come true.
  8. review-skill-coherence (spec scan 7) — read the skills and the entry file against the commit stream since the last retrospective and force a per-skill disposition (confirm-current / update / park / retire); templates/prompts/review-skill-coherence.md.

Commit the retrospective, the conflicts surfaced and the dispositions ruled, the reconciled things, and the skill edits the dispositions imply.

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. today Changed · +29 lines · +16 tokens per session a0ea33d80371
  2. 10d ago First seen · 20 lines · 16 tokens per session scan A 3cd04114ac06

Subscribe to this mod's changes

retrospective is a command published in the GitHub repository JanoshMoshiri/MarkdownLLM (5 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 752 once invoked, about $0.0002 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.