Instructions file
Claude Code instructions for AllanWessels/Bratan, covering rag refiner, what this project is, repo layout, how to work in this repo and run the loop.
2 1mo ago D 3,230 tokens
Skill Claude CodeCodex
Pass model explicitly when dispatching sub-agents. Parent-default inheritance bypasses cost considerations; reserve stronger models for tasks that genuinely need them.
2 1mo ago A 32 tokens
Skill Claude CodeCodex
When a commit changes a component's public API, the same commit must update every test asserting the removed surface — split commits leave CI broken even when each commit is internally consistent.
2 1mo ago A 41 tokens
Skill Claude CodeCodex
When a class of bug keeps slipping through tests, run a coverage-matrix audit first, then fan out fix agents per gap — don't whack-a-mole individual failures.
2 1mo ago A 44 tokens
Skill Claude CodeCodex
Before pushing to CI, validate that your local test run is representative — three predictable axes diverge (gitignored fixtures, dev-only ports, dev-only env vars) and each has a deterministic fix.
2 1mo ago A 49 tokens
Skill Claude CodeCodex
Land every code fix before running the test harness. Use grep + read to debug; the harness is a verifier, not a debugger.
2 1mo ago A 33 tokens
Skill Claude CodeCodex
Tests that mock the layer where the bug lives cannot catch bugs at that layer. Write tests that drive the same code path the user drives, ending at something the user can see.
2 1mo ago A 44 tokens
Skill Claude CodeCodex
When verifying or fixing a multi-layer change, dispatch each test layer and each independent fix as a parallel sub-agent rather than running serially in the main context.
2 1mo ago A 39 tokens
Skill Claude CodeCodex
Before saying "ready, retest", prove the state is clean by running a concrete numbered checklist. Never claim clean state — demonstrate it with real command output.
2 1mo ago A 39 tokens
Skill Claude CodeCodex
Wrap both read and write paths through any client that holds per-path singleton state in a subprocess worker, so on-disk state changes are always reflected without a full process restart.
2 1mo ago A 45 tokens
Skill Claude CodeCodex
When verifier agents share a long-running server process with the user, state that poisons the verifier flows directly into the user's next interaction. End every verifier run with process-level restart and a round-trip health check.
2 1mo ago C 50 tokens
ablation
12Skill Claude CodeCodex
Use this skill to attribute the contribution of each pipeline stage by systematically disabling one stage at a time and re-running eval. Tells the Blue Team whether reranking (or hybrid retrieval, or query rewriting, etc.) is actually paying its keep, and which stage to invest tuning effort in. Reach for it before any…
2 1mo ago A 77 tokens
Skill Claude CodeCodex
Use this skill when the Blue Team needs to tune a small set of numeric hyperparameters (chunk size, top-k, rrfk, top-n for reranker, generation temperature) and the eval call is expensive enough that random or grid search would burn the budget. Bayesian Optimization uses a probabilistic surrogate (Gaussian Process or…
2 1mo ago A 94 tokens
Skill Claude CodeCodex
Use this skill to add a post-generation pass that verifies every citation in the LLM's answer actually appears in (and is supported by) the cited chunk. Reach for it when the faithfulness score is low even though retrieval is healthy, or when invented citations are surfacing as a failure category.
2 1mo ago A 69 tokens
Skill Claude CodeCodex
Use this skill when chunks have ambiguous referents that hurt retrieval — for example, a paragraph starting "It supports up to 10,000 connections" where "it" is whatever the document is about. The technique prepends an LLM-generated context block to each chunk before embedding, so the chunk embeds in the right region…
2 1mo ago A 79 tokens
Skill Claude CodeCodex
Use this skill when you need to interpret /reports/latest.json to find the root cause behind multiple failing cases. Reach for it before making changes to the pipeline, so you fix one root cause at a time instead of whacking moles. The output is "here is the cluster, here is the hypothesis, here is the suggested fix…
2 1mo ago A 78 tokens
grid-sweep
17Skill Claude CodeCodex
Use this skill when the Blue Team is tuning 1–2 discrete or low-cardinality parameters (k, topn, rrfk, chunkoverlap) and the Cartesian product is small enough to enumerate exhaustively. Simpler than Bayesian Optimization, with the advantage that every cell of the grid is reported so the result is visually inspectable.
2 1mo ago A 76 tokens
Skill Claude CodeCodex
Use this skill when failures show that vector search is missing exact-token matches (product names, error codes, version numbers, identifiers) or conversely when keyword search is missing semantic paraphrases. This skill documents how to add a BM25 lane alongside the vector lane and merge the results with Reciprocal…
2 1mo ago A 73 tokens
Skill Claude CodeCodex
Use this skill when the Blue Team needs to optimize over a mixed continuous + discrete + categorical space too large for grid search and too rough for Bayesian Optimization's Gaussian-Process surrogate. PSO and its evolutionary cousins (CMA-ES, GA) navigate jagged surfaces by maintaining a population of candidates…
2 1mo ago A 78 tokens
Skill Claude CodeCodex
Use this skill when you need high-level guidance on the structure of a RAG pipeline — what stages it should have, what trade-offs each stage makes, when to add or remove a stage. Reach for it for architectural decisions, not numeric tuning.
2 1mo ago A 58 tokens
Skill Claude CodeCodex
Use this skill when generating new failure-targeting test cases. Documents techniques for producing questions that are diverse, non-trivial, and actually defeat the current pipeline — not paraphrases of existing test cases. Most useful for the red team agent.
2 1mo ago A 57 tokens