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/feature-editnpx skills add swingerman/engineer --skill feature-editgit 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 | $0.00063 | $0.00719 |
| Opus 5 | $0.00032 | $0.00360 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
feature-edit 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
feature-edit
Intent-driven editing of an in-flight feature. The human describes what should now be true; this skill figures out which files and tools to touch and orchestrates the change, including the downstream cascade.
The cascade-owning skill — clarify and refine deliberately stay single-artifact and route multi-artifact propagation here. Mixed mode: the agent proposes an edit plan, the human confirms before any write.
When to use
Any time an existing feature's artifacts must change. checkpoint: null.
Not for: a brand-new capability (discuss); within-one-artifact ambiguity, no behavior change (clarify); validating consistency (consistency-check); cleaning up code (refine).
Workflow
- Resolve + identify the feature — resolve the methodology root + manifest via
${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py(seereferences/resolving.md); locate the feature (slug, branch, or searchfeature.mdtitles/outcomes). - Is this actually an edit? — if the intent is a new capability or too big for one feature, surface it and redirect to
discuss. Stop. - Classify the entry artifact — the highest-level artifact the intent directly changes: outcome/scope →
feature.md; a behavior →acs.md; a GWT detail →spec.md; architecture/phasing →plan.md. - Build the edit plan — the cascade runs strictly downstream (
feature.md → acs.md → spec.md → plan.md); upstream problems are surfaced, never auto-propagated. Per downstream artifact, classify by blast radius: small/mechanical → feature-edit edits directly; substantial → invoke the owning skill (discover-acs/atdd:atdd/plan) in edit-pass mode. - Present the plan; human confirms — show entry artifact, cascade, and how each step is handled. Nothing is written before confirmation.
- Execute — in cascade order: direct edits and owning-skill invocations; regenerate
.build/spec.jsonafter anyspec.mdchange; re-run affected test streams if code exists. If regeneration reveals an upstream problem, stop and surface it. - Sync — update
progress.md(affected checkpoint rows) and the tracker via the driver. - Handoff — emit a summary.
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 · 37 lines · 63 tokens per session scan A 14a376a449a3
feature-edit is a skill published in the GitHub repository swingerman/engineer (144 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 719 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.