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/file-issuenpx skills add dburkart/auto-engineer --skill file-issuegit 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/file-issue)<a href="https://agentmods.dev/skills/dburkart/auto-engineer/file-issue"><img src="https://agentmods.dev/badge/skills/dburkart/auto-engineer/file-issue.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 | $0.00061 | $0.00988 |
| Opus 5 | $0.00030 | $0.00494 |
| Sonnet 5 | $0.00012 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
file-issue 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 3d 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.
file-issue
Files a single GitHub issue against dburkart/auto-engineer with priority and classification labels applied on creation. Keeps the backlog triaged in one step instead of leaving un-labeled issues that pollute the auto-engineer candidate set.
Read docs/agent-playbooks/prioritization.md before running — the label taxonomy, priority rules, and triage policy all live there. This skill is the mechanical front-end for that policy.
Label taxonomy
Priority labels: priority:P0 (critical — blocks core functionality), priority:P1 (high — required for next milestone), priority:P2 (medium — polish and hardening), priority:P3 (low — nice-to-have or future work). Type labels: bug (something isn't working), enhancement (new feature or improvement). Every issue must have exactly one priority:* label and at least one type/area label.
When to invoke
- A merged PR surfaced out-of-scope follow-up work that needs its own issue (auto-engineer step 8, or a human reviewer deferring a nit).
- A
TODO/FIXMEwas introduced that deserves tracking. - The user says "file an issue for …" or invokes
/file-issuedirectly.
Do not use this skill to edit an existing issue — use mcp__github__update_issue for that.
Inputs
Either accept them as free-form arguments after /file-issue, or infer from the invoking context:
- title — imperative phrase, ≤ 72 chars, no emoji.
- motivation — 1–3 sentences on why this matters and what it unblocks.
- work — bulleted sub-tasks, concrete enough to act on cold in a week (file paths, type names, function signatures when known).
- context — relevant commit SHAs, file paths, existing issue numbers, or the PR that surfaced the follow-up.
If any of those are missing and cannot be reasonably inferred, skip the issue silently — do not ask the user. This skill may be called from auto-engineer or other agents where user interaction is not available; asking would block the loop.
Cycle
1. Dedupe
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.
- 3d ago First seen · 98 lines · 61 tokens per session scan A c8624bca5e6c
file-issue is a skill published in the GitHub repository dburkart/auto-engineer (5 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 61 tokens to every session and 988 once invoked, about $0.0003 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.
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.
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.