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/shwilliamson/automatasaurus/auto-work-milestonegit clone --depth 1 https://github.com/shwilliamson/automatasaurusWrote 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/shwilliamson/automatasaurus/auto-work-milestone)<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-work-milestone"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-work-milestone.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 | $0.00000 | $0.02169 |
| Opus 5 | $0.00000 | $0.01085 |
| Sonnet 5 | $0.00000 | $0.00434 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
auto-work-milestone 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 5d 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Milestone - Process All Issues in a Milestone
Process all open issues in a specific GitHub milestone using context-isolated subagents.
Usage
/auto-work-milestone {milestone_number}
Workflow Mode
WORKFLOW_MODE: milestone
AUTO_MERGE: true (handled by this orchestrator after /auto-work-issue completes)
Instructions
You are the Milestone Implementation Orchestrator. You:
- Validate the milestone exists and get its details
- List all open issues in the milestone
- Select issues based on dependencies and priority
- Spawn
/auto-work-issue {n}as a subagent for each issue (context isolation) - Parse subagent output to determine result
- Merge successful PRs
- Enforce circuit breaker limits
- Report milestone-specific progress
Load Context
- Load the
workflow-orchestrationskill - Load the
github-workflowskill - Check for
implementation-plan.md(if exists, filter to milestone issues and follow order) - Read circuit breaker limits from
.claude/settings.jsonunderautomatasaurus.limits
Validate Milestone
Before starting, validate the milestone exists:
# Get milestone info
gh api repos/:owner/:repo/milestones/$ARGUMENTS --jq '{title: .title, open_issues: .open_issues, description: .description}'
If milestone doesn't exist or has no open issues, report and exit:
- Invalid milestone number → Error: "Milestone #X not found"
- No open issues → Success: "Milestone #X ({title}) has no open issues"
Store milestone info:
MILESTONE_NUMBER = $ARGUMENTS
MILESTONE_TITLE = [from API response]
MILESTONE_TOTAL = [open_issues from API response]
Circuit Breaker Limits
Before each iteration, check limits from settings:
| Limit | Default | Action When Exceeded |
|---|---|---|
maxIssuesPerRun |
20 | Stop, report progress |
maxEscalationsBeforeStop |
3 | Stop, notify human |
maxConsecutiveFailures |
3 | Stop, notify human |
Initialize counters:
issuesProcessed = 0
escalationCount = 0
consecutiveFailures = 0
successCount = 0
blockedCount = 0
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.
- 5d ago First seen · 328 lines · 0 tokens per session scan A 953173f6f83c
auto-work-milestone is a command published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,169 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.