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/seednpx skills add dburkart/auto-engineer --skill seedgit 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/seed)<a href="https://agentmods.dev/skills/dburkart/auto-engineer/seed"><img src="https://agentmods.dev/badge/skills/dburkart/auto-engineer/seed.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 | $0.00077 | $0.05773 |
| Opus 5 | $0.00039 | $0.02887 |
| Sonnet 5 | $0.00015 | $0.01155 |
| Haiku 4.5 | $0.00008 | $0.00577 |
Grade E, and why
seed scanned grade E with 4 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| Rust | `COPY --chown=agent:agent rust-toolchain.toml /tmp/toolchain/ 2>/dev/null || true`<br>`RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \| sh -s -- -y --default-toolchain stable --profile minimal -- Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `templates/settings.local.json` | `<target>/.claude/settings.local.json` | Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls <target>/.claude/skills/ 2>/dev/null Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Rust | `COPY --chown=agent:agent rust-toolchain.toml /tmp/toolchain/ 2>/dev/null || true`<br>`RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \| sh -s -- -y --default-toolchain stable --profile minimal -- How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seed
Configures the auto-engineer toolkit for a target project. Always runs from within this auto-engineer repo — it never copies itself. Reads templates from templates/ (relative to this repo's root), substitutes {{PLACEHOLDER}} values, and writes the results into the target project.
Does not touch any pre-existing .claude/ directory in the target. Skills are written into .claude/skills/ but only for skill names that don't already exist there. settings.local.json and .claude/.gitignore are only created if absent.
When to invoke
- User says "seed a project", "set up auto-engineer", "configure the loop", or
/seed. - Accepts an optional positional argument: the path to the target project.
- If no path is given as an argument, ask for it as the first action (before any detection).
Step 0 — Get the target path
If the user did not provide a path as an argument, ask:
"What's the path to the project you want to seed? (absolute or relative to your home directory)"
Resolve to an absolute path. Verify the directory exists. If it doesn't exist, ask whether to create it. Abort with a clear error if the user declines creation and the path is missing.
All subsequent file reads and writes use <target>/ as the root.
Phase 1 — Detect project state
cd into the target directory for all detection commands. Determine whether this is an existing project (has .git) or a new project (no git history yet).
Existing project detection
Run these in parallel from <target>/:
# GitHub owner/repo
gh repo view --json owner,name --jq '"\(.owner.login)/\(.name)"'
# Current authenticated user (for assignee default)
gh api user --jq .login
# Existing labels
gh label list --json name,description --limit 100
# CI workflows
ls .github/workflows/*.yml 2>/dev/null || true
Also scan for tech stack indicators by checking for file existence in <target>/:
| File | Stack | Default commands |
|---|---|---|
Cargo.toml |
Rust | build: cargo build, test: cargo test, format: cargo fmt --all, lint-fix: cargo clippy --fix --allow-dirty --allow-staged && cargo fmt --all |
go.mod |
Go | build: go build ./..., test: go test ./..., format: gofmt -w ., lint-fix: golangci-lint run --fix |
package.json |
Node/TS | build: npm run build, test: npm test, format: npm run format, lint-fix: npm run lint --fix |
pyproject.toml or setup.py |
Python | build: python -m build, test: pytest, format: ruff format ., lint-fix: ruff check --fix . |
Makefile |
Make-based | Read the Makefile for targets: look for build, test, lint, format |
| None of the above | Unknown | Will need to prompt user |
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 · 430 lines · 77 tokens per session scan E 2bfaf1247b65
seed is a skill published in the GitHub repository dburkart/auto-engineer (5 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 77 tokens to every session and 5,773 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it E with 4 findings (downloads and executes remote code, reads agent configuration directories, enumerates other installed skills). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…