Agent
Apply atomic per-finding code fixes triggered by code-review output. 3-tier verify (re-read → syntax-check → fallback). Defers logic-bug fixes to humans.
210 8d ago A 41 tokens
original MIT
Agent
Use when producing a structured map of a codebase — tech stack, architecture, conventions, and entry points — for downstream phases to consume.
210 8d ago C 35 tokens
original MIT
Agent
Review individual marketing-copy pieces for tone, clarity, CTA strength, and conversion fundamentals. Trigger per piece pre-publish.
210 8d ago A 30 tokens
original MIT
Agent
Use when managing a multi-cycle debug session that needs checkpoint/continuation across context resets.
210 8d ago A 24 tokens
original MIT
Agent
Use when investigating a bug using the scientific method with hypothesis tracking.
210 8d ago B 18 tokens
original MIT
Agent
Flag publishConfig drift, lock-in version skew, dep version mismatches. Trigger before any release wave.
210 8d ago A 28 tokens
original MIT
Agent
Critique UI/visual design artefacts on hierarchy, contrast, alignment, consistency, and intent. Trigger per design review pass.
210 8d ago A 32 tokens
original MIT
Agent
Use when a phase has ambiguities, gray areas, or unresolved decisions that need adaptive interrogation before SPEC can lock. Dispatched by ijfw-spec-phase, but can be called directly when the user says 'discuss this phase', 'what's unclear', 'interrogate the ambiguities', 'help me decide', '/ijfw-discuss-phase'.…
210 8d ago A 92 tokens
original MIT
Agent
Verify factual claims in generated docs against live code. Trigger after doc generation in plan/handoff/CHANGELOG steps.
210 8d ago A 29 tokens
original MIT
Agent
Writes/updates CHANGELOG.md + README.md from commit log + handoff. Trigger before ship-gate.
210 8d ago A 28 tokens
original MIT
Agent
Pre-flight canonical install/update/uninstall in scratch tmpdir scoped to diff. Run before ship-gate.
210 8d ago D 29 tokens
original MIT
Agent
Use when dispatching an implementation subagent that may hit issues requiring auto-fix vs ask-architectural decisions.
210 8d ago A 28 tokens
original MIT
Agent
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
210 8d ago A 31 tokens
original MIT
Agent
Verify E2E flows that span multiple subagent worktrees after Phase D wiring.
210 8d ago A 24 tokens
original MIT
Agent
Sentence-level line editing pass for prose: rhythm, clarity, repetition, dialogue tags. Trigger after a draft is content-complete.
210 8d ago A 31 tokens
original MIT
Agent
Tally session token cost vs milestone budget. Warn when a phase is on track to exceed allocation.
210 8d ago A 29 tokens
original MIT
Agent
Maintain a canonical lore/world bible — characters, places, rules, factions. Source of truth for continuity checks.
210 8d ago A 29 tokens
original MIT
Agent
Audit research method, bias surface, source quality, and traceability for a single research artefact. Trigger per artefact pre-publish.
210 8d ago A 34 tokens
original MIT
Agent
Detect plot, character, timeline, and setting continuity breaks across book chapters. Trigger after each revise pass.
210 8d ago A 32 tokens
original MIT
Agent
Verify every phase contract criterion has a covering test. Flag coverage gaps; propose skeleton tests.
210 8d ago A 27 tokens
original MIT
Agent
Map new files in plan to closest existing analog. Auto-fires at plan-time so subagents onboard via PATTERNS.md.
210 8d ago A 32 tokens
original MIT
Agent
Compare plan items against existing codebase BEFORE dispatch. Catches re-spec of infrastructure that already exists.
210 8d ago A 26 tokens
original MIT
Agent
Monitor subagent telemetry; auto-resume truncated subagents from last checkpoint. Trigger when waves are in flight.
210 8d ago A 31 tokens
original MIT
Agent
Ships releases: version bump, tag, CI publish watch, rollback if smoke fails. Trigger when phase passes ship-gate.
210 8d ago A 30 tokens
original MIT