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 skills add white1024/agent-nextup --skill two-axis-reviewgit clone --depth 1 https://github.com/white1024/agent-nextupWrote 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/skills/white1024/agent-nextup/two-axis-review)<a href="https://agentmods.dev/skills/white1024/agent-nextup/two-axis-review"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/two-axis-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/white1024/agent-nextup/two-axis-review"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/two-axis-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00062 | $0.01162 |
| Opus 5.5 | $0.00025 | $0.00465 |
| Sonnet 5.5 | $0.00012 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
two-axis-review 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
two-axis-review — conventions and spec, never merged
Goal: two independent reports on the same change — does it follow how this project writes code, and does it do what the task asked — each finding citing its source, so neither axis can hide a failure on the other.
1. Pin the change
Take the fixed point the work started from (a commit, a branch, the merge base with the main branch; ask if it is not obvious). Capture git diff <fixed-point>...HEAD and the commit list once. Confirm the reference resolves and the diff is not empty before going further.
2. Find the spec source
- The tasks this change implements: ids in the commit messages, the task you were working, or the one named in the request. Read each with
get_task— the description says what it delivers and how anyone will know it works. - With the spec module on: each task's delta under
tasks/<id>/specs/, and the current spec it modifies (get_spec). - Nothing found: ask. If there truly is no spec, the spec axis reports exactly that.
3. Find the standards source
Every document in the project that says how code here is written — a coding-standards file, CONTRIBUTING.md, the conventions section of the project docs — plus the lint and format configuration. On top of those, the conventions axis always carries this baseline of code smells. Each one is a judgement call, never a hard violation, and a documented project rule overrides it:
- Mysterious name → rename until it says what it holds.
- Duplicated code → extract the shared shape.
- Feature envy → move the logic onto the data it keeps reaching for.
- Data clump → the fields that travel together want a type.
- Primitive obsession → a domain concept deserves its own small type.
- Repeated switch → one map or one polymorphic call both sites share.
- Shotgun surgery → what changes together belongs together.
- Divergent change → one module, one reason to change.
- Speculative generality → delete hooks the task never asked for.
- Message chain → hide the walk behind one call.
- Middle man → call the real target directly.
- Refused bequest → composition instead of inheritance.
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 · 79 lines · 62 tokens per session scan A 8730ee8e3913
two-axis-review is a skill published in the GitHub repository white1024/agent-nextup (2 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 1,162 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-19.
Other skills, from other repositories
bot-reviewer
Review Telegram, Discord, Slack, and other chat bot code for interaction safety, authorization, state, delivery, and resilience using the actual platform and framework contract. Read-only review with explicit coverage and unverified gates.
go-concurrency-reviewer
Review selected Go concurrency paths for goroutine ownership, channels, cancellation, synchronization, memory-model, and shutdown defects under actual version and workload contracts.
go-performance-reviewer
Review assigned Go performance paths and claims using workload, profiling, benchmark, allocation, GC, contention, I/O, pool, and cache evidence.
go-reviewer
Review selected Go code for architecture, API, SQL, error, resource, and value-semantics defects using actual toolchain, module, framework, and caller contracts.
go-error-reviewer
Review selected Go failure paths for error identity, wrapping, inspection, cleanup, cancellation, recovery, and public diagnostic contracts.
go-modernizer
Review assigned Go modernization opportunities against actual language, toolchain, module API, compatibility, and behavior constraints; propose ordered migrations without applying edits.