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/clarifynpx skills add swingerman/engineer --skill clarifygit 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 | $0.00045 | $0.00581 |
| Opus 5 | $0.00023 | $0.00291 |
| Sonnet 5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
clarify 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clarify
Resolve ambiguities in one DAE artifact through an iterative interview. A cross-cutting quality gate — runs on any artifact at any pipeline stage.
The clarify pattern is also embedded inside artifact-producing skills for their own in-flight ambiguities; this standalone skill is for ad-hoc cleanup after the fact.
When to use
On any one of: feature.md, acs.md, spec.md, plan.md, CHARTER.md. Invoked as /engineer.clarify <slug> <artifact> or /engineer.clarify <path>.
Not for: cross-artifact contradictions (consistency-check); changing what a feature does (feature-edit); resolutions that cascade across files (clarify the source here, then feature-edit).
Workflow
- Resolve + load — resolve the methodology root + manifest via
${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py(seereferences/resolving.md); locate the target artifact. Also load its parent contract for grounding (feature.mdfor acs/spec/plan;CHARTER.mdfor feature.md). - Identify ambiguities — within this one artifact: language interpretable two ways, underspecified requirements, undefined domain terms, unclear scope boundaries, internal contradictions. Cross-artifact contradictions are out of scope (→
consistency-check). If none found, say so and stop. - Resolve one at a time — per ambiguity, quote the ambiguous line and ask one question — multiple-choice (AskUserQuestion) when bounded, open-ended otherwise. Iterate until resolved or the user stops.
- Edit in place — encode each resolution into the target artifact; show old→new, confirm before writing. Edit only the target artifact.
- Flag downstream staleness — do NOT cascade. Identify downstream artifacts a resolution may have invalidated; list them in the handoff; recommend
feature-edit(which owns cascade). - Handoff — emit a summary.
Handoff
Emit per ${CLAUDE_PLUGIN_ROOT}/references/handoff-summary.md. checkpoint: null. If downstream staleness flagged: human_action_needed: yes, recommended_next: "/engineer.feature-edit to propagate".
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 · 35 lines · 45 tokens per session scan A 86473e72c00a
clarify is a skill published in the GitHub repository swingerman/engineer (144 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 581 once invoked, about $0.0002 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.