Kit Consolidator — Development agent for Claude Code
Use proactively when ledger observations are unconsolidated — the stop-gate names it (map M-14).
How to install Kit Consolidator
Installs to ~/.claude/agents/oskarc-meta-kit-builder-kit-consolidator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/oskarc/meta-kit-builder/HEAD/agents/kit-consolidator.md -o ~/.claude/agents/oskarc-meta-kit-builder-kit-consolidator.md Restart Claude Code, or start a new session, for it to be picked up.
What Kit Consolidator does
name: kit-consolidator description: Use proactively when ledger observations are unconsolidated — the stop-gate names it (map M-14). The only writer of candidates. Merges observations into held candidates, counts evidence by whether it came from a different reading, sets certainty, flags candidates due for pioneer review, fades stale ones, resolves outcomes and keeps the scores — none of which score the pioneer. Never decides a stage the pioneer owns and never sees review batches or sealed k
Alternatives in Development
- Seam Analyzer — Hunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held to 2.2k ★
- Dashclaw Drift Auditor — Audits DashClaw's drift-prone hardcoded counts and version stamps — SDK method counts (Node/Python), MCP tool/ 297 ★
- Ana Learn — Ana Learn — quality gardener 32 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kit Verifier
Use proactively when a contract is implemented and tests, observations or a pioneer confirmation exist — the s
Kit Recorder
Use when the main session must add observations to the ledger while a review batch is open and the ledger is c
Pattern Contention
Finds jobs a codebase does two or more ways — competing helpers, libraries, or idioms for one concern — counts
Us Risk Assessor
US stock risk analyst. Evaluates stop usability, liquidity and volatility fit for top candidates (0-15 = Stop
Meta Review
Council Meta-review role. Reads hypotheses, objections and comparisons for the run, synthesises recurring weak
Issue Namer
Step 8 of the review pipeline. Reads phrase groups, the where-in-the-app phrases and the App Store listing; na
Related Skills
Tune Skill
Agent skill that audits and fine-tunes a skill that already exists: triggering descriptions, sibling overlaps,
Skill Picker
Forget skill names? Local catalog that turns 'which skill for X?' into 2-4 clickable candidates — and flags du
Open Contribute
Agent Skills that take you from "I want to contribute to open source" to a submitted pull request — and measur