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/swingerman/engineer/controlnpx skills add swingerman/engineer --skill controlgit clone --depth 1 https://github.com/swingerman/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 | $0.00057 | $0.00816 |
| Opus 5 | $0.00028 | $0.00408 |
| Sonnet 5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
control scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
control
Serve the control surface: a read-only, live web view of the project — a feature × checkpoint pipeline board and an architecture map (layer nodes
- import edges + health). It reads the same artifacts the pipeline writes; it
does not dispatch, edit, or write anything. This is the
rendercapability (${CLAUDE_PLUGIN_ROOT}/references/host-capabilities.md) as a served page.
When to use
/engineer.control— "where does everything stand?" across the whole project.- After a work session, to eyeball pipeline progress and architecture health.
Not for: running/assigning/pausing work (management is not built yet — this
is visualization only); a single feature's status (prime-context / next).
Workflow
- Resolve the methodology root + effective
autonomy_levelvia${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py(seereferences/resolving.md). - Render rules (
references/host-capabilities.md): the served view is an enhancement, never a gate, and stays on127.0.0.1(feature names/paths are fine locally, never on a shared URL). A terminal fallback always exists:python3 ${CLAUDE_PLUGIN_ROOT}/scripts/dae_control.py --json <root>prints the same state blob — use it when a browser isn't wanted or available. - Launch the server, keyed by autonomy:
low→ ask once ("open the live control surface at 127.0.0.1?"), then go.medium/high→ launch and announce in one line. Run it backgrounded so the session stays interactive, e.g.python3 ${CLAUDE_PLUGIN_ROOT}/scripts/dae_control.py --port 8770 <root> &, then surface the printedhttp://127.0.0.1:PORT/URL. If the port is taken the server falls back to an ephemeral one and prints that URL instead.
- Report the URL and that it is read-only + live (auto-refreshes every few seconds). Remind the human to stop it (Ctrl-C / kill the process) when done.
Notes
- Two tabs: Pipeline (every feature × the 9 checkpoints, status-colored,
click a row for detail) and Architecture (layer nodes, actual import
edges,
may_not_importrules, violated edges in red, cycles flagged). - The architecture map only shows real edges for languages
dae_archparses (.py/.js/.ts/…); layers over other languages render as nodes with no edges. Feature-relationship and roadmap views are not built yet.
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 · 56 lines · 57 tokens per session scan A 6ef899072d3f
control is a skill published in the GitHub repository swingerman/engineer (144 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 816 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 2026-08-30.
Other skills, from other repositories
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
work-summary
Generates a project dashboard from MCP work items. Default is a lean, attention-first view: what's in flight, what's blocked, what to do next, what's queued. Use when the user says: project status, what's active, show me the dashboard, work summary, what should I work on, project health, what's blocked, where did I…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
bmad-dev-story
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".
bmad-editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure.