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.
git clone --depth 1 https://github.com/alexander-akhmetov/programmatorWrote 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.
[](https://agentmods.dev/commands/alexander-akhmetov/programmator/plan-to-ticket)<a href="https://agentmods.dev/commands/alexander-akhmetov/programmator/plan-to-ticket"><img src="https://agentmods.dev/badge/commands/alexander-akhmetov/programmator/plan-to-ticket.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00024 | $0.00890 |
| Opus 5 | $0.00012 | $0.00445 |
| Sonnet 5 | $0.00005 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
plan-to-ticket 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan to Ticket
Converts a Claude Code plan file into a programmator-compatible ticket with phases, tasks, and acceptance criteria.
Instructions
-
Find the most recent plan file:
ls -lt ~/.claude/plans/*.md | head -1 -
Read the full plan content
-
Determine project context: Use current git repo folder name, or "misc" if not in a repo
-
Extract title: Get the title from the plan's first
#heading -
Extract phases and tasks from the plan:
Phases (high-level stages):
- Each major implementation step/section becomes a phase
- Phase format:
- [ ] Phase N: Name - brief actionable description - Keep phase count proportional to plan complexity (don't force 5 phases on a 2-step plan)
- Phase names must be actionable (what to do, not just a label)
- If the plan already has checkbox phases, reuse them as-is
Tasks (concrete work items grouped by phase):
- Break each phase into specific, self-contained changes
- Group tasks under
### Phase N: Namesubheadings - Each task = one logical unit (one function, one endpoint, one component)
- Use plan text plus conversation context to resolve file paths. Add a
Files:line (e.g.,Files: Create \path/to/new`, Modify `path/to/existing`) per phase group. Include only paths that are explicit or strongly implied. Omit theFiles:` line entirely if no paths are confidently known. - If the plan involves code changes, include test items per task group (write tests, run tests)
- If a phase has no granular detail in the plan, create 1-2 tasks summarizing that phase's work
-
Generate acceptance criteria: From the plan's goal and overview, derive 2-4 concrete "done when" conditions. Each must be verifiable (not subjective). If the plan mentions tests or verification steps, include those.
-
Create an empty ticket to get an ID and file path:
ticket create "[project] title" --type task -
Write the ticket file directly at
$TICKETS_DIR/<id>.mdwith the complete frontmatter and body:
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.
- 6d ago First seen · 98 lines · 24 tokens per session scan A 78833b0aafba
plan-to-ticket is a command published in the GitHub repository alexander-akhmetov/programmator (2 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 890 once invoked, about $0.0001 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.
Other commands, from other repositories
octo-schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
octo-scheduler
Manage the Claude Octopus scheduled workflow runner daemon.
prd-score
Score an existing PRD against the 100-point AI-optimization framework.
schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
multi-repo-swarm
Coordinate AI swarms across multiple repositories, enabling organization-wide automation and intelligent cross-project collaboration.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.