research-workflow

Go/no-go checkpoint before an expensive or irreversible run (high-impact-checkpoint).

Build or review an implementation-ready equation digest from source PDFs, with rendered-PDF verification states, traceability, license/firewall notes, and errata/conflict handling.

Inspect or enable the research-workflow hook decision log (RWF_HOOK_DEBUG).

Reference-parity audit against an external reference, loading the matching domain lens.

Capture a reproducibility contract for the current work — env lock, seeds, precision, inputs, commit.

Use this agent to adversarially verify equation-digest rows against rendered PDFs or trusted publisher sources before they are marked implementation-ready. Typical triggers include "verify these equation rows", "check this digest against the PDF", "audit the Hurley equations", and any request to promote `needs-pdf-check` rows to `verified`. Do not use for ordinary literature summaries, code review after equations are implemented, or licensing decisions around reference code.

Use when you have a result you are about to trust — to red-team it against confirmation bias and the stable-but-wrong failure mode (numerical artifact, latent bug, boundary effect, or a mundane alternative explanation that fits the same data). Produces the strongest attacks plus the cheapest discriminating test for each. Don't use for reviewing CODE (→ scientific-code-reviewer and the Review cluster), the neutral close-out format (→ verification-gate), reporting the result's uncertainty budget (→ uncertainty-reporting-gate), or explaining a convergence/refinement-floor behavior (→ numerical-method-validation).

Use when relying on code, math, or facts the AI assistant itself produced — apply EXTRA scrutiny precisely because the model's signature failure is confident fabrication: hallucinated library APIs, plausible-but-wrong algebra, invented constants/citations, and tests written to pass rather than to catch. The stance that points generic skepticism at the assistant's own output. Don't use as the concrete check itself — route to the specific gate: API existence (→ verify against docs), formulas (→ derivation-before-implementation), constants/citations (→ provenance-of-constants), result size (→ plausibility-envelope), test/claim integrity (→ evidence-first-execution).

Use when a research session produces meaningful results and you need durable manifests, payloads, plot scripts, and a completion note so later sessions can reason from artifacts instead of memory. Don't use for the in-the-moment command discipline (→ evidence-first-execution), the go/no-go close-out (→ verification-gate), or pinning the runtime environment itself (→ reproducible-environment-contract).

Use when a result or model rests on simplifying assumptions, approximations, fixed parameters, or regime-of-validity choices — keep an explicit running ledger of what each result depends on, so when an assumption later breaks you know exactly which conclusions die with it. Don't use for citing the source of a value (→ provenance-of-constants), recording a decision and its rationale (→ decision-log-and-commits), quantifying the numeric error a kept assumption induces (→ uncertainty-reporting-gate), or noting a regime/caveat a *paper* established as you read it (→ reading-notes-discipline) — this ledger is for your own project's assumptions.

Use when writing plotting code for astrophysics figures — author publication-grade plots in the house style: the jaxstroviz theme/helpers as source of truth, seaborn perceptually-uniform colormaps (mako/vlag), CVD-safe categorical palettes with color×marker redundancy, log/linear axis choice, LaTeX (not unicode) labels with CGS/solar units, uncertainty/overlays. Don't use to audit an existing figure's craft (→ plot-craft-reviewer), what a figure lets you conclude (→ figure-interpretation-guard), whether it honestly shows the data (→ plot-faithfulness-inspector), chart-type/design ideation (→ plot-design-inspector), or journal submission specs (→ publication-figure-validator).

12 hooks across 4 events