find-wasted-code

스타6

포크0

업데이트2026년 7월 15일 19:54

Use ONLY when the operator runs "/find-wasted-code" (or explicitly asks to "scan the repo for dead-end tool calls / broken links / missing helpers / footgun configs / silent push-through"). Statically scans THIS repo for friction footguns and writes a tracked report to docs/wasted-code/report.md. Manual-trigger ONLY — do NOT auto-invoke; the skill carries disable-model-invocation and no hook wires it. Read-only except the one report write. Findings are review candidates, never auto-fixes. Do NOT use for token/transcript economy (/token-waste-audit), for process ceremony (/find-wasted-effort), or for CLI/Flow drift health (/fusebase-health).

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

출처

fusebase-dev

fusebase-dev/fusebase-flow

GitHub 저장소 열기 Creator 저장소 보기

다운로드

관련 직업SOC

SOC 직업 분류 기준

소프트웨어 개발자컴퓨터 및 수학직·SOC 15-1252

파일 탐색기

3 개 파일

SKILL.md

readonly

이 저장소의 다른 Skills

같은 저장소

lightweight-lane

fusebase-dev/fusebase-flow

Use at Specify to classify a ticket Full vs Lightweight, and whenever a change looks small / reversible / low-risk ("small fix", "tweak", "hotfix", "drop pretty-printing", "bump a constant"). Operationalizes FR-21 — ceremony proportional to change size. Defines the eligibility gate, the change-note artifact, the one-pass build→verify→deploy procedure, and mid-flight promotion. Do NOT use for risky/uncertain work, schema/data migrations, security/permission changes, new public contracts needing a decision, unknown-root-cause diagnostics, or large features — those take the Full lane.

2026-07-146

role-discipline

fusebase-dev/fusebase-flow

ALWAYS load at session start. After self-attesting, Read references/<role>.md for your role (Product Owner / AI Developer / Architect / Deploy phase) — role-specific don't-list, exact refusal phrasing for FR violations, and recovery pointers; shared cross-role protocols live in this file. Mandatory; not on-demand.

2026-07-146

product-owner

fusebase-dev/fusebase-flow

Use when the operator types /product-owner, asks to activate Product Owner, start a Product Owner or PO session, or searches /product in Codex for Fusebase Flow project management. Do NOT use for implementing code; route implementation to the AI Developer role.

2026-07-116

module-size-discipline

fusebase-dev/fusebase-flow

Use when planning tasks that touch big source files, when an edit would push a file past the module-size ceiling, when the pre-commit module-size ratchet warns or blocks, or when generating policies/module-size-baseline.txt. Operationalizes FR-25 — module-size ratchet (ceiling default 800; over-ceiling files may shrink, never grow; extraction along a responsibility seam is in-scope, not scope creep). Do NOT use for docs/markdown size (FR-23 owns docs), to force decomposition of an existing monolith (that is its own explicit ticket), or to judge split quality by regex (seam-vs-mechanical is semantic — code-review owns it).

2026-07-106

release-deploy-reporting

fusebase-dev/fusebase-flow

Use ONLY when verification passed AND operator explicitly says "prepare deploy" / "draft deploy" / "ship it"; drafts deploy handoff, captures deploy hash + probes + smoke, advises spec DRAFT→DONE flip. Do NOT auto-invoke; operator triggers explicitly.

2026-07-106

business-logic-guardian

fusebase-dev/fusebase-flow

Use ONLY when a business-logic doc exists — docs/<app>/business-logic-index.md (AI-default retrieval index), docs/<app>/business-logic.md (human narrative), or docs/en/business-logic.md (the app-business-docs canonical for Fusebase CLI teams) — before fixes/improvements that touch business behavior. Treats the documented business logic as a guard layer — the fix must not silently break documented behavior. Pairs with FR-20 zoom-out. If none of these docs exist, this skill does nothing (silent no-op) — do NOT auto-create any of them. Not for net-new features with no documented logic.

2026-07-106

name	find-wasted-code
description	Use ONLY when the operator runs "/find-wasted-code" (or explicitly asks to "scan the repo for dead-end tool calls / broken links / missing helpers / footgun configs / silent push-through"). Statically scans THIS repo for friction footguns and writes a tracked report to docs/wasted-code/report.md. Manual-trigger ONLY — do NOT auto-invoke; the skill carries disable-model-invocation and no hook wires it. Read-only except the one report write. Findings are review candidates, never auto-fixes. Do NOT use for token/transcript economy (/token-waste-audit), for process ceremony (/find-wasted-effort), or for CLI/Flow drift health (/fusebase-health).
disable-model-invocation	true
source_inspiration	conceptual-only
license_status	clean-room-original
fusebase_flow_version	4.5
risk_level	low
invocation	manual
expected_outputs	["a Mode-A chat summary plus a tracked report at docs/wasted-code/report.md","per-rule findings (W1-W4) each labelled broken/confirmed or candidate/inconclusive, evidence + suggested fix + why-it-might-be-intentional","a Coverage section (W5 swallow baseline, unresolved references, skipped inputs) — silence is auditable, not clean"]
related_workflows	["eight-phase-flow.md"]
hook_dependencies	["none"]

Find Wasted Code (static friction-footgun audit)

The active, static inverse of a papercuts log. A papercuts tool is passive — an agent must notice friction and file it. This audit scans the repo for the same north-star footguns and writes them down, so nobody has to notice first:

Agents hit friction constantly — dead-end tool calls, broken links, missing helpers, footgun configs — and silently push through without telling anyone.

It is the third audit sibling, on a distinct axis:

	`/find-wasted-code` (this)	`/find-wasted-effort`	`/token-waste-audit`
Axis	code-per-friction (footguns)	process-per-outcome (ceremony)	tokens-per-rule (consumption)
Inputs	repo source: docs, skills, commands, hooks, settings	Flow artifacts on disk	Claude transcripts
Output	`docs/wasted-code/report.md` (TRACKED)	`state/audit/<date>.md` (gitignored)	`state/audit/<date>.md` (gitignored)
Trigger	`/find-wasted-code` ONLY (never auto)	`/find-wasted-effort` (auto-invocable)	`/token-waste-audit`

How to run

python hooks/local/find-wasted-code.py (if python is missing, python3 …). Optional: --print (summary only, no write), --date YYYY-MM-DD (deterministic in-report date), --selftest (per-rule golden fixtures), --root PATH.
Read the report it wrote (docs/wasted-code/report.md): the per-rule findings + the Coverage section.
Interpret every row as a review candidate, never a verdict or an auto-fix. broken/confirmed = the target is provably absent from repo state; candidate/inconclusive = needs human judgment. Ambiguous references are listed under Coverage → Unresolved, never as defects.
Output a Mode-A chat summary: totals by rule/severity, the W5 baseline counts, and the top confirmed broken items. Do not paste raw file contents.
The report is tracked (papercuts philosophy — it shows up in diffs). It is redaction-safe by construction and will not trip the pre-commit secret scanner. Fixes are the operator/PO's call — this audit surfaces, it does not mutate.

The rules (one per north-star category)

Per-rule signatures, the conservative confirmed-vs-coverage contract, and the false-positive classes: references/rule-catalog.md and references/false-positive-examples.md. Cite them; don't restate.

#	Rule	What it confirms (`broken`)	What it leaves as Coverage
W1	Dead-end tool/script references	a root-explicit interpreter/`./`-run path (`bash hooks/local/<name>.sh`) that is absent	cwd-ambiguous paths, placeholders, design docs (specs/backlog excluded)
W2	Broken internal links	a Markdown link whose path is absent, or whose anchor no heading yields (target slug-confident)	non-Markdown anchors, slug-ambiguous targets (→ `inconclusive`), external/placeholder dests
W3	Missing helpers	a shell `source` of a static root-explicit script that is absent	`related_workflows`/`hook_dependencies` (ambiguous field shape) → unresolved
W4	Footgun config	a settings hook `command` wired to a handler that does not exist (silently never fires)	dead policy keys (no stdlib YAML) — future
W5	Silent push-through	— (no confirmed findings in v1)	swallowed-error baseline (broad/trivial `except`; shell `2>/dev/null`/`\|\| true`/`\|\| return 0`) as review candidates

Conservative by construction (load-bearing)

A finding is confirmed ONLY when provable from repository state. Everything ambiguous is Coverage, never a defect — so the audit never blocks or annoys the operator with a false positive. This is the same "don't block the human operator" floor the framework holds everywhere. W5 is deliberately a measured baseline, not a finding list: this repo intentionally fails open/closed in many places (best-effort cleanup, fail-closed scanners), so generic swallow-detection cannot be low-false-positive — the operator reviews the baseline and annotates intentional swallows with find-wasted-code: ignore W5 — <reason>.

Trigger isolation

Claude Code: hard guarantee via disable-model-invocation: true — the model cannot auto-load this skill; only /find-wasted-code runs it.
Other adapters (Codex/Cursor/Gemini): advisory — the narrow description above will not match ordinary work, and no hook wires the analyzer. Invoke by name or /prompts:find-wasted-code.
No lifecycle hook (SessionStart/Stop/PostToolUse/UserPromptSubmit) references this skill or its analyzer. It is inert until the operator triggers it.

Read-only-to-the-project

The analyzer writes ONLY docs/wasted-code/report.md, containment-checked to inside the repo, symlink/hardlink-refusing, atomic, and sentinel-guarded (it will not overwrite a hand-authored file lacking its generated-file sentinel). No memory, overlay, spec, policy, or source edits. Fixes are proposed, never applied.

Non-Claude surfaces

Invoke the find-wasted-code skill by name and run the analyzer directly (python hooks/local/find-wasted-code.py); it is stdlib-only and surface-independent. Metrics come from repo state, so there is no transcript dependency.

Clean-room note

Original Fusebase Flow content. Designed after reviewing public agent-friction and self-improvement projects (papercuts, agentlogs, friction-logging-toolkit, self_improving_coding_agent, opencode-autolearn) for concepts only — the north-star framing and severity vocabulary. No third-party code, prompts, skill files, or hook scripts are copied; the analyzer, rule contract, and report format are clean-room original. See docs/source-map.md.