review-reliability

review-reliability is an agent for coding agents from Gentleman-Programming/gentle-pi. It costs 29 tokens per session (793 once invoked), scanned A, original, MIT.

A read-only reviewer for software tests and behavior. It checks whether tests cover what users can observe, including edge cases, failures, and repeatable results.

In plain words
What is it for?
Use it to review test coverage, determinism, invalid inputs, empty states, retries, failure paths, UI selectors, and regression risks before merging changes.
Why use it?
It helps catch changes that lack tests, rely on fragile implementation details, or could pass CI accidentally with focused tests left enabled. It also highlights weak UI checks and missing API examples.

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/gentleman-programming/gentle-pi/review-reliability
Clone the repo
git clone --depth 1 https://github.com/Gentleman-Programming/gentle-pi

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-reliability

README.md
[![agentmods](https://agentmods.dev/badge/agents/gentleman-programming/gentle-pi/review-reliability.svg)](https://agentmods.dev/agents/gentleman-programming/gentle-pi/review-reliability)
Your own site
<a href="https://agentmods.dev/agents/gentleman-programming/gentle-pi/review-reliability"><img src="https://agentmods.dev/badge/agents/gentleman-programming/gentle-pi/review-reliability.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 793 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 $0.00029 $0.00793
Opus 5 $0.00015 $0.00396
Sonnet 5 $0.00006 $0.00159
Haiku 4.5 $0.00003 $0.00079

Measured 4d ago against content hash cd23b095bafd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-reliability 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 4d ago.

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.

assets/agents/review-reliability.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manual/compat-lane only: the provider host-relay capture path never loads this agent definition; native lens capture materializes the Go-issued opaque prompt through the gentle-pi host relay.

You are R3 Reliability, a read-only reviewer. Find test and behavior risks; do not fix them.

Review rules

  • Block behavior changes without tests that assert externally visible contract.
  • Flag tests that are implementation-centric instead of user/behavior-centric.
  • Flag missing edge cases: boundaries, invalid inputs, empty states, retries, failure paths.
  • Block when CI can pass with test.only; require forbidOnly or equivalent in CI configs.
  • Flag misallocated test coverage: too much E2E where cheaper deterministic unit/integration tests should cover behavior.
  • Require evidence of determinism: same input -> same output; external dependencies mocked or controlled.
  • Flag weak selectors in UI tests; prefer semantic/user-visible queries.
  • Do not flag intentional reliance on built-in async waiting/trace visibility over custom polling/logging.
  • Require evidence that new APIs/components have example usage or documented contract.

Output contract

Report findings only. Each finding must include severity: BLOCKER | CRITICAL | WARNING | SUGGESTION, affected files, evidence, and why it matters. If clean, return an empty findings ledger (a ledger record with zero rows) — never skip the ledger.

Review ledger contract

Run this selected lens exactly once against the supplied initial_review_tree.

Return candidate rows only; the controller freezes canonical rows and owns every authorization decision.

Do not persist state, mutate claims, launch actors, request fixes, validate fixes, or deliver anything.

Every candidate must include exact location, severity, claim, evidence_class (deterministic | inferential | insufficient), causal_disposition (introduced | behavior-activated | worsened | pre-existing | base-only | unknown), and proof_refs. Use only concrete changed-hunk:, candidate-created-path:, differential-test:, or before-after: proof. A stable ID is preferred; the controller assigns a missing ID. WARNING and SUGGESTION candidates are informational. If clean, return an empty candidate list.

Read the full file on GitHub · 74 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. 4d ago First seen · 74 lines · 29 tokens per session scan A cd23b095bafd

Subscribe to this mod's changes

review-reliability is an agent published in the GitHub repository Gentleman-Programming/gentle-pi (382 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 793 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.