/verify

name: verify
description: Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF path / arXiv URL / pasted text), maps claims to codebase, emits verification table with match status and severity.
argument-hint: <paper> [--scope <glob>] [--program <program.md>] [--strict] [--dim <F,H,E,N,C>] [--codemap] [--no-codemap]
allowed-tools: Read, Write, Bash, Grep, Glob, Agent, WebFetch, TaskCreate, TaskUpdate, AskUserQuestion
effort: medium
disable-model-invocation: true

<constants>

HARD_CUTOFF: 900  # seconds — advisory; Agent() runs in background and cannot be interrupted mid-flight

</constants>

<objective>

Paper-vs-code consistency audit. After `research:scientist` implements method from paper, verify implementation matches paper claims. Audits five dimensions — formula matching, hyperparameter parity, eval protocol, notation consistency, citation chain. Emits verification table with match status and severity.

NOT for: running experiments (use `/research:run`); judging experimental methodology (use `/research:judge`); literature search (use `/research:topic`); general code review (use `/develop:review` (requires `develop` plugin)). Verify audits implementation-vs-paper fidelity only — does not evaluate whether paper's claims are valid.

</objective>

<workflow>

Agent Resolution

`research:scientist` same plugin as this skill — no fallback needed if research plugin installed. Scientist handles all five audit dimensions in single spawn to preserve cross-dimension context (e.g., notation inconsistency explaining formula mismatch needs holistic paper understanding).

Verify Mode (Steps V1–V6)

Triggered by `verify <paper>` where `<paper>` is PDF path, arXiv URL, or multi-line quoted text.

**Task tracking**: create tasks for V1, V2, V3, V4, V5, V6 at start — before any tool calls.

Step V1: Parse paper input

**Input resolution** (priority order):

1. Path ending `.pdf` — read via Read tool (use `pages: "1-20"` for large PDFs; iterate with subsequent page ranges if needed — max 20 pages per Read call) 2. URL matching `arxiv.org` — convert `abs/<id>` to `https://arxiv.org/pdf/<id>` for actual content fetching (e.g., `ARXIV_URL="${ARXIV_URL//arxiv.org\/abs\//arxiv.org\/pdf\/}"`). Use WebFetch (`timeout: 30000`). No separate abstract-page fetch — title/authors/year come from the PDF's first page. 3. URL matching `*.pdf` or `doi.org` — WebFetch (`timeout: 30000`) 4. Multi-line quoted text block — treat as literal paper content 5. No paper argument — stop: `"No paper provided. Usage: /research:verify <paper.pdf|arxiv-url|'pasted text'> [--scope <glob>]"`

**Pay for the paper once**: whatever the source above, write resolved paper content to `$RUN_DIR/paper.md` (Write tool, right after run-dir block below creates `$RUN_DIR`) — V3 spawn prompt passes that path, never re-inlines text, never re-fetches (a 20-page paper re-inlined is 15-25K tok billed twice).

From paper content, extract:

• **Header**: title, authors, year (for report)
• **Claims table**: each claim = `{id, section, claim_text, type}` where type is one of: `formula`, `hyperparameter`, `eval`, `architecture`, `result`
• Focus on: equations with concrete terms, specific hyperparameter values, evaluation protocols (metric names, split names, preprocessing steps), architectural specifics, reported numeric results

**Unsupported flag check**: load and follow the protocol below. Supported flags for this skill: `--scope`, `--program`, `--strict`, `--dim`, `--codemap`, `--no-codemap`.

# loads: unsupported-flag-protocol.md
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
_RESEARCH_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/resolve_shared.py" 2>/dev/null)  # timeout: 5000
[ -z "$_RESEARCH_SHARED" ] && { echo "! Plugin path resolution failed"; exit 1; }
echo "$_RESEARCH_SHARED" > "${TMPDIR:-/tmp}/research-shared-${CSID}"  # cold resolve — every later site reads this sentinel instead of re-running python
cat "$_RESEARCH_SHARED/unsupported-flag-protocol.md"

**Codemap auto-detection** — structural context (blast-radius, importers, coverage) for the audited codebase; on by default when codemap installed + index found. `--no-codemap` opts out; `--codemap` is strict (fail if unavailable). Note: `--codemap` is independent of `--strict` (audit strictness).

# timeout: 5000
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
# Prints the resolved mode and writes true/false to research-verify-codemap-enabled-${CSID};
# exits 1 (already reporting `! BLOCKED`) when --codemap is strict but codemap is unavailable.
CODEMAP_RAW=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/codemap-flag.py" research-verify "$ARGUMENTS") || exit 1

> loads: codemap-gates.md

When `CODEMAP_RAW` ≠ `off`:

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
IFS= read -r _RESEARCH_SHARED < "${TMPDIR:-/tmp}/research-shared-${CSID}" 2>/dev/null || _RESEARCH_SHARED=""  # warm read (Check 41)
cat "$_RESEARCH_SHARED/codemap-gates.md"

Follow Gate A and Gate B.

**Pre-compute run directory** — persist `RUN_DIR` and `OUT` to temp files so V3/V4/V5 (separate Bash shells) can reload them (ADV-H20):

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
BRANCH=$(git branch --show-current 2>/dev/null | tr '/' '-' || echo 'main')  # timeout: 3000
DATE=$(date -u +%Y-%m-%d)  # timeout: 3000
RUN_DIR=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_research}/bin/make_run_dir.py" "verify" ".experiments" 2>/dev/null)  # timeout: 5000
mkdir -p .reports/research
BASE="verify-$BRANCH-$DATE"; OUT=".reports/research/$BASE.md"; COUNT=2; while [ -f "$OUT" ]; do OUT=".reports/research/${BASE}-${COUNT}.md"; COUNT=$((COUNT+1)); done
# persist for V3/V4/V5 (fresh shell each Bash call) — v