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.
npx agentmods add commands/andkirby/markdown-ticket/implementgit clone --depth 1 https://github.com/andkirby/markdown-ticketWhat 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 | $0.02858 |
| Opus 5 | $0.00000 | $0.01429 |
| Sonnet 5 | $0.00000 | $0.00572 |
| Haiku 4.5 | $0.00000 | $0.00286 |
Grade A, and why
implement 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDT Implementation Orchestrator (v10)
Execute tasks from a task list with constraint verification after each task.
Core Principle: Verify TDD (RED→GREEN), scope boundaries (flag/STOP), structure, and no duplication after each task.
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).
Execution Modes
| Command | Behavior |
|---|---|
/mdt:implement {CR-KEY} |
Interactive — auto-detect part or prompt |
/mdt:implement {CR-KEY} --prep |
Execute prep (refactoring) tasks |
/mdt:implement {CR-KEY} --part {X.Y} |
Target specific part |
/mdt:implement {CR-KEY} --all |
Run all tasks, pause at part boundaries |
/mdt:implement {CR-KEY} --continue |
Resume from last incomplete |
/mdt:implement {CR-KEY} --task {N.N} |
Run specific task only |
Execution Steps
Step 1: Load Context and Discover Part
1a. Detect mode:
| Condition | Mode | tasks_file | tests_file | Test Expectation |
|---|---|---|---|---|
--prep flag |
prep | prep/tasks.md |
prep/tests.md |
GREEN (preserve) |
--part X.Y flag |
part | part-X.Y/tasks.md |
part-X.Y/tests.md |
RED (TDD) |
Single part-*/tasks.md |
part (auto) | that part | matching tests | RED |
Multiple part-*/tasks.md |
part (prompt) | user selects | matching tests | RED |
prep/tasks.md has unchecked items |
prep (auto) | prep/tasks.md |
prep/tests.md |
GREEN |
| No part folders | single | tasks.md |
tests.md |
RED |
All paths relative to {TICKETS_PATH}/{CR-KEY}/.
If both prep (incomplete) and part tasks exist, prompt user: [Continue prep (recommended)] [Proceed to feature].
1b. Set CR status to In Progress:
mcp__mdt-all__update_cr_status(project=PROJECT_CODE, key=CR-KEY, status="In Progress")
1c. Load {tasks_file} — extract: scope boundaries, shared patterns/imports, test coverage mapping.
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.
- yesterday First seen · 354 lines · 0 tokens per session scan A 93d164951d23
implement 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 2,858 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.