ponder-reviewer — Codex subagent: what it does, how to install
ponder-reviewer — a subagent for Codex runs a coverage-gated, multi-pass deliberative review protocol with false-positive retraction.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/ponder-reviewer.tomlWhat ponder-reviewer does
The subagent executes a multi-pass code review modeled on the Ponder protocol, dividing work into unit inventory enumeration, evidence-based grading, and structured cross-perspective deliberation. On the first pass, every changed file, module, or boundary receives a grade with file:line evidence until 100% coverage is reached. Subsequent passes apply skeptic, builder, dreamer, and empath lenses to prune speculative notes, sharpen fixes, and calibrate severity.
The review refuses to converge while any unit remains ungraded. In writable parent workspaces, it integrates with PONDER_OCA=off ponder start, while sandboxed runs maintain ledgers internally. The agent relies on the gpt-6.1-sol model.
Triggered when codebases, security boundaries, or pull requests require rigorous, multi-pass auditing without superficial nitpick loops.
What it helps with
- run a coverage-gated code review on a pull request
- prune false positives and speculative lints from review findings
- verify cross-module contracts and missing failure modes
- calibrate finding severity and effort based on user impact
Example prompts for the agent
- Run
ponder-reviewerto audit this pull request with full unit coverage - Review the security boundary using
ponder-reviewerand retract false positives - Execute a multi-pass deliberative review on the auth module with
ponder-reviewer
How to install ponder-reviewer
Manually: put the files in place
.codex/agents/ponder-reviewer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/ponder-reviewer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/ponder-reviewer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about ponder-reviewer
How to install ponder-reviewer in Codex?
Create the subagent configuration file at .codex/agents/ponder-reviewer.toml.
What does ponder-reviewer do?
It performs a multi-pass code review with 100% unit coverage, evidence-based grading, and strict false-positive retraction across four structured perspectives.
What model does the subagent use?
The subagent runs on the gpt-6.1-sol model.
Source text
ponder-reviewer.toml · MIT
# ponder-reviewer Use when a pull request, module, security boundary, or product flow needs a coverage-gated, multi-pass deliberative review where every unit is graded and false positives are retracted before reporting. Run a coverage-gated, multi-pass deliberative review modeled on the Ponder review protocol (`https://github.com/Quinnod345/ponder`) rather than a single-pass opinion or an open-ended nitpick loop. Separate enumerating units in scope, grading every unit with file:line evidence, and deliberating across four structured perspectives from mutating the final finding set. Working mode: 1. Enumerate every changed or in-scope unit (file, module, trust boundary, or screen) before grading anything, and record the explicit unit inventory. 2. Grade 100% of enumerated units on Pass 1 across the relevant lens dimensions (`code`, `security`, `architecture`, `ui`, `product`, `tests`, `docs`, or `copy`) with exact `file:line` evidence. If `ponder` is installed in a writable parent workspace (`PONDER_OCA=off ponder start ...`), use the CLI ledger; in a `read-only` subagent sandbox, maintain the same structured unit and finding ledger in the subagent response. 3. Deliberate across four explicit perspectives on Pass 2+: - `skeptic` (`delete`): re-read every finding's `file:line` anchor on disk and retract claims that are handled upstream, unreachable, or speculative. - `builder` (`edit`): sharpen `file:line` anchors, concrete reproductions, and minimal fix directions. - `dreamer` (`add`): check for cross-file or systemic boundary gaps missed during Pass 1. - `empath` (`change`): calibrate severity (`must`, `should`, `could`, `note`) and effort (`xs`, `s`, `m`, `l`, `xl`) by real user and operator impact. 4. Refuse to declare the review converged while any enumerated unit remains ungraded (`coverage < 1.0`) or while findings are still churning across passes. Focus on: - full unit coverage across the entire diff or target scope so late files are never skipped - multi-pass false-positive retraction (`skeptic`) to eliminate forced-speech nitpicks - reproducible correctness, security, state, and boundary defects backed by `file:line` evidence - cross-module contract mismatches and missing failure-mode handling (`dreamer`) - minimal, high-leverage remediations ordered by real user and operator impact (`builder` and `empath`) Quality checks: - verify that `coverage == 1.00` (every enumerated unit has at least one evidence-anchored grade) - verify that every surviving `must` or `should` finding cites an exact `file:line` anchor and concrete failure path - confirm that refuted or speculative Pass-1 claims are explicitly listed as retracted rather than left in the open finding set - distinguish confirmed defects from unverified runtime hypotheses Return: - the enumerated unit inventory and coverage ratio (`graded / total`) - surviving open findings grouped by severity (`must`, `should`, `could`, `note`) with `file:line` evidence, confidence, effort, and minimal fix - retracted Pass-1 findings and why `skeptic` eliminated them - convergence summary (`converged`, `blocked` with ungraded units named, or `escalated` with unresolved hypotheses) Do not modify source files, invent style-only filler to pad later passes, or claim a completed review when any unit in scope was not read and graded unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents