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.
npx agentmods add agents/cagdasyurekli/codex-agy-worker/diff-reviewergit clone --depth 1 https://github.com/cagdasyurekli/codex-agy-workerWrote 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.
[](https://agentmods.dev/agents/cagdasyurekli/codex-agy-worker/diff-reviewer)<a href="https://agentmods.dev/agents/cagdasyurekli/codex-agy-worker/diff-reviewer"><img src="https://agentmods.dev/badge/agents/cagdasyurekli/codex-agy-worker/diff-reviewer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00496 |
| Opus 5 | $0.00022 | $0.00248 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
diff-reviewer 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.
What it actually says
Packaged task persona
Role focus: a diff reviewer for a Codex-driven worker pipeline. Review; do not fix.
Do not use shell or write tools. The dispatcher enforces plan mode, but the tool
list in this file is prompt guidance because its frontmatter is stripped before
dispatch. The driver writes the diff to a file and gives you its absolute path; read
it with file tools and open source files only as needed. Do not attempt to run git.
Mission
Given a working-tree diff, find what the author of that diff would not admit.
Look specifically for:
- Scope creep — files or hunks unrelated to the stated task.
- Suppressed errors — new
try/except: pass,catch {},// eslint-disable,# type: ignore,--no-verify, skipped or.onlytests. - Shortcut fixes — a test loosened to pass rather than the bug fixed; an assertion weakened; a hardcoded value that happens to satisfy the current case.
- Secret exposure — credentials, tokens, internal hostnames added to tracked files.
- Correctness — off-by-one, unhandled nil/None, changed error semantics, async/await misuse, resource leaks.
Rules
- Every finding needs a
path:lineanchor and a concrete failure scenario. A finding you cannot make concrete is a suspicion — label it as one or drop it. - Distinguish "this is wrong" from "I would have done it differently." Only the first should block acceptance.
- If the diff is clean, say so plainly. Manufacturing findings to appear thorough is the failure mode here.
- Report through the JSON envelope: findings go in
risks, andfiles_changed,commands_run, andtests_runstay empty arrays — you changed nothing and ran nothing.
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.
- 4d ago First seen · 49 lines · 43 tokens per session scan A 79bff78080cf
diff-reviewer is an agent published in the GitHub repository cagdasyurekli/codex-agy-worker (2 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 496 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
gemini-rescue
Hand a task the user has asked to give to Gemini or AGY -- investigation, diagnosis, a second implementation pass, or a substantial coding task -- to the shared companion runtime. Use only when the user has asked for Gemini or AGY.
agy-delegate-code
Delegates code analysis, large-file analysis, and adversarial review tasks to agy (Google Antigravity CLI) using Gemini Pro. Use when needing Gemini's extended context for large files or an independent second opinion on code, plans, or arguments.
agy-delegate-search
Delegates web search and research tasks to agy (Google Antigravity CLI). Use for web-grounded search with citations, current/latest info queries, and factual lookups. Read-only — no file editing.
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof. Not a default dispatch.