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/hundia/autospec/execute-ticketgit clone --depth 1 https://github.com/Hundia/autospecWhat 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 | $0.00981 |
| Opus 5 | $0.00000 | $0.00491 |
| Sonnet 5 | $0.00000 | $0.00196 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
execute-ticket scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| API change | Run API test suite. If new endpoint, demonstrate it works via curl/fetch | How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Ticket
Execute a ticket from the backlog following Spec-Driven Development methodology.
Usage
/execute-ticket [ticket_number]
Example: /execute-ticket 4.3
Instructions
Note: When running inside an Orchestrator+Agent session, the agent briefing file (agents/sprint-X-brief.md) takes precedence over interactive backlog discovery. Read it first.
When this command is invoked:
-
Read the backlog to find the specified ticket:
- Read
specs/backlog.md - Locate the ticket by number (e.g., 4.3 = Sprint 4, Ticket 3)
- Note the ticket's owner, model recommendation, status, and dependencies
- Read
-
Check dependencies:
- Verify prerequisite tickets are marked ✅ Done
- If dependencies are incomplete, notify the user and stop
-
Read relevant docs FIRST (before touching code):
- Check
docs/for existing documentation related to this ticket's subsystem - Understanding existing architecture prevents rework and regressions
- Check
-
Update backlog status:
- Change ticket status from 🔲 Todo to 🔄 In Progress
- Edit
specs/backlog.mdwith the status change
-
Read relevant spec file based on ticket type:
- Backend tickets →
specs/02_backend_lead.md - Frontend tickets →
specs/03_frontend_lead.md - Database tickets →
specs/04_db_architect.md - DevOps tickets →
specs/06_devops_lead.md - QA tickets →
specs/05_qa_lead.md - UI tickets →
specs/10_ui_designer.md - Check for linked feature specs mentioned in the sprint
- Backend tickets →
-
Implement the ticket:
- Follow patterns and conventions from the relevant spec files
- Write clean, typed code following project standards
- Add appropriate error handling
-
QA Verification (MANDATORY — scale to change type):
Change Type QA Required Bug fix Reproduce bug first, apply fix, verify the exact user flow passes API change Run API test suite. If new endpoint, demonstrate it works via curl/fetch UI change Run UI tests. Verify page renders correctly Database migration Verify migration applies cleanly, test affected endpoints Docs/config only No QA needed — mark ✅ directly Full-stack feature Run full test suite. Add test cases if needed
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 · 122 lines · 0 tokens per session scan A c5ce284c77fe
execute-ticket is a command published in the GitHub repository Hundia/autospec (4 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 981 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.