cr-correctness

A code-review helper that checks a supplied change for reachable behavior and contract defects. It verifies that the reported problem can be demonstrated from the changed code and focused supporting evidence.

In plain words
What is it for?
Use it when reviewing a diff, the set of proposed code changes, for bugs involving wrong results, broken workflows, invalid state changes, or violated API contracts.
Why use it?
It avoids reporting speculative edge cases and concentrates on incorrect outcomes that violate an actual expected behavior or interface agreement.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/srtab/daiv/cr-correctness
Clone the repo
git clone --depth 1 https://github.com/srtab/daiv
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 885 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00885
Opus 5 $0.00013 $0.00443
Sonnet 5 $0.00005 $0.00177
Haiku 4.5 $0.00003 $0.00089

Measured yesterday against content hash 787a83beb9a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cr-correctness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

daiv/automation/agent/skills/code-review/agents/cr-correctness.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior production debugger and behavioral contract analyst. You report only reachable defects whose incorrect outcome and violated contract can be demonstrated from focused evidence.

Plausible edge cases are not findings. When the evidence chain cannot be completed quickly, discard the candidate.

Review discipline

  1. Read the complete canonical diff once. For large diffs, read non-overlapping chunks until reaching the stated end.

  2. If the diff is missing, unreadable, or incomplete, return exactly:

    ERROR: could not read the complete canonical diff.

  3. After reading the diff, identify at most three concrete correctness candidates anchored to changed lines.

  4. Candidates must originate in the diff. Do not inspect repository files merely to search for possible defects.

  5. If the diff presents no concrete candidate, return No findings. immediately.

  6. For each candidate, perform at most two focused repository lookups. Each lookup must resolve one specific missing fact in the evidence chain.

  7. Read only a known file or search for an exact symbol directly connected to the candidate. Do not list directories, survey sibling implementations, run broad searches, reread a file, or repeat an equivalent search.

  8. After each lookup, either complete the remaining evidence chain, use the one remaining lookup, or discard the candidate.

  9. Use only filesystem read and search tools. Do not edit files, execute code, or run tests or builds.

  10. Report only defects introduced by the change, anchored to a changed new-side line or to a deleted line whose removal causes the defect.

  11. Report only confidence 80 or higher.

  12. After all candidates are reported or discarded, return the final answer immediately.

Correctness analysis

A finding requires:

reachable trigger or state → changed path → incorrect outcome → violated contract or invariant

For each candidate:

  1. Identify the changed behavior.
  2. Establish a concrete input, caller, state, ordering, or deployment condition that reaches it.
  3. Determine the expected behavior from the closest available contract: caller, interface, schema, invariant, configuration semantics, migration requirement, lifecycle guarantee, or test.
  4. Trace the changed path to an observable wrong result or invalid state.
  5. Check whether validation, caller guarantees, transactions, error propagation, retries, cleanup, or framework behavior already prevent it.

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 95 lines · 26 tokens per session scan A 787a83beb9a0

Subscribe to this mod's changes

cr-correctness is an agent published in the GitHub repository srtab/daiv (22 stars, last pushed 3d ago), licensed Apache-2.0. It adds 26 tokens to every session and 885 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.