A post-implementation review command for capturing lessons from a conversation and selected workflow documents, then proposing updates to those documents.

Use it to review implemented behavior, architecture, testing needs, unresolved issues, and approved updates to the relevant MDT documents.

It turns confirmed lessons and specification changes into documented improvements instead of leaving them only in conversation history.

reflection — Command by andkirby

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/andkirby/markdown-ticket/reflection

Clone the repo

git clone --depth 1 https://github.com/andkirby/markdown-ticket

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,196 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	$0.00000	$0.02196
Opus 5	$0.00000	$0.01098
Sonnet 5	$0.00000	$0.00439
Haiku 4.5	$0.00000	$0.00220

Measured 2d ago against content hash 69f52b558eb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reflection 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 2d 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.

prompts/mdt/commands/reflection.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Ticket Reflection Workflow (v4)

Capture post-implementation learnings from the conversation and selected workflow artifacts, then encode approved updates into the CR and any chosen MDT documents. Focus on artifact-level insights and specification adjustments only.

Core Principle: Reflection starts from the documents that shaped the work. Ask which workflow documents should be read, recommend which of them should be updated based on the changes that were actually made, then record approved updates with concrete artifact references.

User Input

$ARGUMENTS

Session Context

Use {TICKETS_PATH} in all file path templates below (if it's not defined read ticketsPath from .mdt-config.toml).

You MUST consider the user input before proceeding.

Source Ownership

Use this routing table when recommending update targets:

Change Type	Update Target
Implemented behavior, constraints, acceptance semantics	`requirements.md`
Structure, ownership, integrations, runtime flow, prerequisites	`architecture.md`
Verification intent, required checks, regression coverage	`tests.md`
Unresolved issues, compromises, follow-up cleanup	`debt.md`
Session summary, links, user-approved notes	`CR Section 8 (Clarifications)`
Context note with no source document change	`CR only`

Execution Steps

Load CR Context

Use mdt-all:get_cr with mode="full":
- Parse CR key, project code, and current status
- If the ticket doesn't exist, abort and instruct the user to create the CR first
- If the status is Rejected, warn that reflection may not be appropriate
- If the status is not Implemented, confirm the user wants to reflect on in-progress work
Select Documents to Review

Detect which of these documents exist under {TICKETS_PATH}/{CR-KEY}/:
- requirements.md
- bdd.md
- architecture.md
- tests.md
- tasks.md
- debt.md
- poc.md
- domain.md
- domain-audit.md
- prep/architecture.md, prep/tests.md, prep/tasks.md

Read the full file on GitHub · 272 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.

2d ago First seen · 272 lines · 0 tokens per session scan A 69f52b558eb0

Subscribe to this mod's changes

reflection is a command published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,196 tokens. 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.

Code review Learning and teaching Testing

reflection

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

MDT Ticket Reflection Workflow (v4)

User Input

Session Context

Source Ownership

Execution Steps

What this file has done since we first saw it

Other commands, from other repositories

learn

component

memory-store

review

no-vibe

teach-me-testing