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 skills/dburkart/auto-engineer/auto-managernpx skills add dburkart/auto-engineer --skill auto-managergit clone --depth 1 https://github.com/dburkart/auto-engineerWrote 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/skills/dburkart/auto-engineer/auto-manager)<a href="https://agentmods.dev/skills/dburkart/auto-engineer/auto-manager"><img src="https://agentmods.dev/badge/skills/dburkart/auto-engineer/auto-manager.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 | $0.00110 | $0.03798 |
| Opus 5 | $0.00055 | $0.01899 |
| Sonnet 5 | $0.00022 | $0.00760 |
| Haiku 4.5 | $0.00011 | $0.00380 |
Grade A, and why
auto-manager 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 4d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-manager
Takes either a specific scoping issue or a fuzzy topic, and drives it through to a merged epic without requiring the user to manually file each sub-issue, plan workstreams, or coordinate subagents. The skill owns five phases:
- Discover (fuzzy input only) — explore the open backlog + codebase to gather candidate issues and surface gaps; present a scope proposal for the user to approve before doing anything destructive.
- Scope — read the spec / approved scope, inspect the codebase, file well-scoped sub-issues.
- Refine — iterate with the user on the filed plan (rescope, fold, drop).
- Plan — partition issues into independent workstreams with a dependency graph.
- Orchestrate — spawn
/auto-engineersubagents in parallel (worktree-isolated, background) and respawn as predecessors land.
Read the tracker playbook first: {{PLAYBOOK_TRACKER}}. All tracker operations in this skill — listing the backlog, fetching/editing/commenting/closing issues, filing new ones — go through its recipes. Do not invoke gh issue ... or mcp__github__*_issue directly.
{{#if PLAYBOOK_SDLC}}Then read these shared playbooks:
{{PLAYBOOK_SDLC}}{{PLAYBOOK_PRIORITIZATION}}{{PLAYBOOK_PR_REVIEW}}{{/if}}
Also read the sibling skills you'll call into:
.claude/skills/file-issue/SKILL.md— used in phase 1 for every sub-issue filed..claude/skills/auto-engineer/SKILL.md— hard dependency; phase 4 is meaningless without it.
Hard requirements
/auto-engineermust exist in this project. If not, stop and tell the user.{{PLAYBOOK_TRACKER}}must exist. Without it this skill has no way to read or mutate the backlog.- The repo must have
gh, a code-review gate (CODEOWNERS + reviewers, a review bot, or equivalent), and CI wired up — auto-engineer's loop assumes these. (Note:ghis required for PR/CI operations regardless of tracker; for GitHub-tracker projects it's also used by the tracker playbook's recipes.)
When to invoke
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.
- 4d ago First seen · 232 lines · 110 tokens per session scan A ea8001dd0acd
auto-manager is a skill published in the GitHub repository dburkart/auto-engineer (5 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 110 tokens to every session and 3,798 once invoked, about $0.0006 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 skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
okx-task-watch
监听任务进展 / 帮我盯着任务 / 任务有动静告诉我 / 历史消息 / 未读消息 / 未决策 / 待决策 / 继续监听 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A user-session task-notification monitor: live long-poll via okx-a2a user watch (also drains backlog of past/missed/unread events on entry) plus…
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.