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/syncnpx skills add dburkart/auto-engineer --skill syncgit clone --depth 1 https://github.com/dburkart/auto-engineerWhat 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 | $0.00071 | $0.02294 |
| Opus 5 | $0.00036 | $0.01147 |
| Sonnet 5 | $0.00014 | $0.00459 |
| Haiku 4.5 | $0.00007 | $0.00229 |
Grade A, and why
sync 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 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.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sync
Two-way sync between a seeded project and this auto-engineer repo's templates. Detects drift in skills, Dockerfile, and scripts; lets you resolve each divergence interactively.
This is a harness-internal development tool. It lives only in .claude/skills/sync/ — the seed skill never copies it to target projects.
When to invoke
- User says "sync skills", "sync with project", "sync templates", or invokes
/sync. - Accepts an optional positional argument: path to the seeded project to sync with.
Step 0 — Get the target path
If not provided as an argument, ask:
"What's the path to the seeded project you want to sync with? (absolute path)"
Resolve to an absolute path. Verify the directory exists. Abort with a clear error if not found.
All reads and writes to the target project use <target>/ as the root. The auto-engineer repo root (<ae-repo>) is the directory that contains both .claude/ and templates/ as direct children — from this skill file's location at .claude/skills/sync/SKILL.md, that is three levels up.
Step 1 — Discover sync candidates
Sync covers three artifact groups:
Group A — Skills
- Template side: subdirectories under
<ae-repo>/templates/skills/that contain aSKILL.md. - Target side: subdirectories under
<target>/.claude/skills/that contain aSKILL.md.
Classify each skill name:
| Classification | Condition |
|---|---|
| Paired | Present in both templates/skills/<name>/ and <target>/.claude/skills/<name>/ |
| Template-only | In templates/skills/ but not in target (never seeded, or intentionally absent) |
| Target-only | In <target>/.claude/skills/ but no template counterpart (e.g. seed, sync, new user skills) |
All three groups participate in the interactive resolution loop:
- Paired skills: full pull / push / diff / skip menu.
- Template-only skills: offer
[p] pullto seed the skill into the target, or[s] skip. - Target-only skills: offer
[P] pushto promote to templates, or[s] skip.
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 · 230 lines · 71 tokens per session scan A 9e7b22877bc5
sync is a skill published in the GitHub repository dburkart/auto-engineer (5 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 71 tokens to every session and 2,294 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…