assess

assess is a command for coding agents from andkirby/markdown-ticket. It costs 0 tokens per session (2,987 once invoked), scanned A, original, MIT.

A code-fitness assessment command that examines the code affected by a proposed architecture change. It checks existing tests and identifies behaviors that should be protected before refactoring.

In plain words
What is it for?
Use it before designing an architecture change to inspect test coverage, list return values, errors, and side effects, and choose a testing or change-splitting approach.
Why use it?
It shows whether the code is safe to change and highlights the risk of breaking behavior that is not covered by tests. It helps choose between integrating, refactoring, or splitting the work into separate change requests.

Command

Part of the mdt plugin — 1 skill, 16 commands, 5 agents, 1 hook shipped together

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/assess
Clone the repo
git clone --depth 1 https://github.com/andkirby/markdown-ticket

Or install mdt, the plugin that ships this one along with the rest of its 1 skill, 16 commands, 5 agents, 1 hook.

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 assess

README.md
[![agentmods](https://agentmods.dev/badge/commands/andkirby/markdown-ticket/assess.svg)](https://agentmods.dev/commands/andkirby/markdown-ticket/assess)
Your own site
<a href="https://agentmods.dev/commands/andkirby/markdown-ticket/assess"><img src="https://agentmods.dev/badge/commands/andkirby/markdown-ticket/assess.svg" alt="Measured on agentmods" height="20"></a>
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 2,987 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 $0.00000 $0.02987
Opus 5 $0.00000 $0.01494
Sonnet 5 $0.00000 $0.00597
Haiku 4.5 $0.00000 $0.00299

Measured 3d ago against content hash fe364ed2f366, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assess 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 3d 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/assess.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Code Fitness Assessment Workflow (v2)

Assess affected code before architecture design. Surfaces the decision: integrate as-is, refactor inline, or split CRs.

Core Principle: Know the state of what you're touching before deciding how to touch it.

User Input

$ARGUMENTS

Session Context

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

Output

File {filename} has {None/Partial} test coverage. Refactoring without tests risks breaking undocumented behavior.

Behaviors identified for testing:

Behavior Type Risk if Untested
{function} returns {shape} Return contract Silent shape change
{function} throws {ErrorType} Error contract Wrong error type
{function} emits {event} Side effect Missing events

Recommendation: Add behavioral preservation tests before proceeding.

Options: [A] Add tests inline (expand CR scope) [B] Create test CR first (CR-TEST blocks this CR) [C] Proceed without tests (accept risk)


### Step 5: Determine Recommendation

Based on findings:

**Option 1 (Just Integrate)** when:
- All files ✅ Healthy
- Or: ⚠️ files not in direct change path
- Or: Deadline pressure justifies deferring

**Option 2 (Refactor Inline)** when:
- ⚠️ files in direct change path
- Total refactor effort ≤ 4 hours
- Refactoring improves the feature work

**Option 3 (Split CRs)** when:
- 🔴 Critical files in change path
- Total refactor effort > 4 hours
- Refactoring benefits multiple future CRs
- High-risk files (volatile + low tests)
- **🔴 No test coverage on files being refactored** (test CR first)

### Step 6: Present Assessment

```markdown
## Code Fitness Assessment: {CR-KEY}

### Summary

| Verdict | Count | Action |
|---------|-------|--------|
| ✅ Healthy | {N} | Proceed |
| ⚠️ Concerning | {N} | Consider refactoring |
| 🔴 Critical | {N} | Refactor required |

### Affected Files

Read the full file on GitHub · 391 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. 3d ago First seen · 391 lines · 0 tokens per session scan A fe364ed2f366

Subscribe to this mod's changes

assess is a command published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,987 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.